Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4771 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 29.7274. Min Range: -29.7274
Max Act: 29.6024. Min Act: -0.1700
Data Index: 5560953 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 29.7274. Min Range: -29.7274
Max Act: 29.7274. Min Act: -0.1700
Data Index: 4735318 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 29.7274. Min Range: -29.7274
Max Act: 29.7274. Min Act: -0.1699
Data Index: 6934722 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 29.7274. Min Range: -29.7274
Max Act: 29.4774. Min Act: -0.1699
Data Index: 7979778 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 29.7274. Min Range: -29.7274
Max Act: 29.3524. Min Act: -0.1700
Data Index: 4586914 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 29.7274. Min Range: -29.7274
Max Act: 29.3524. Min Act: -0.1700
Data Index: 83340 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 29.7274. Min Range: -29.7274
Max Act: 29.3524. Min Act: -0.1699
Data Index: 8549434 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 29.7274. Min Range: -29.7274
Max Act: 29.2274. Min Act: -0.1700
Data Index: 1710967 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 29.7274. Min Range: -29.7274
Max Act: 29.1024. Min Act: -0.1700
Data Index: 3039397 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 29.7274. Min Range: -29.7274
Max Act: 28.9774. Min Act: -0.1700
Data Index: 4717996 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 29.7274. Min Range: -29.7274
Max Act: 28.8524. Min Act: -0.1700
Data Index: 5560951 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 29.7274. Min Range: -29.7274
Max Act: 28.8524. Min Act: -0.1700
Data Index: 2149027 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 29.7274. Min Range: -29.7274
Max Act: 28.8524. Min Act: -0.1700
Data Index: 3593541 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 29.7274. Min Range: -29.7274
Max Act: 28.8524. Min Act: -0.1700
Data Index: 4717995 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 29.7274. Min Range: -29.7274
Max Act: 28.8524. Min Act: -0.1700
Data Index: 7134563 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 29.7274. Min Range: -29.7274
Max Act: 28.7274. Min Act: -0.1700
Data Index: 3012474 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 29.7274. Min Range: -29.7274
Max Act: 28.6024. Min Act: -0.1700
Data Index: 4963779 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 29.7274. Min Range: -29.7274
Max Act: 28.6024. Min Act: -0.1699
Data Index: 5560959 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 29.7274. Min Range: -29.7274
Max Act: 28.6024. Min Act: -0.1700
Data Index: 4257656 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 29.7274. Min Range: -29.7274
Max Act: 28.6024. Min Act: -0.1700
Data Index: 5019503 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19