Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2828 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.7509. Min Range: -10.7509
Max Act: 10.7509. Min Act: -0.1700
Data Index: 1610074 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7509. Min Range: -10.7509
Max Act: 10.5009. Min Act: -0.1700
Data Index: 6599704 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7509. Min Range: -10.7509
Max Act: 10.4384. Min Act: -0.1700
Data Index: 5786861 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7509. Min Range: -10.7509
Max Act: 10.3759. Min Act: -0.1700
Data Index: 7409086 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7509. Min Range: -10.7509
Max Act: 10.3759. Min Act: -0.1700
Data Index: 1926157 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7509. Min Range: -10.7509
Max Act: 10.3134. Min Act: -0.1700
Data Index: 1069023 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7509. Min Range: -10.7509
Max Act: 10.3134. Min Act: -0.1700
Data Index: 5778146 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7509. Min Range: -10.7509
Max Act: 10.3134. Min Act: -0.1700
Data Index: 7850693 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7509. Min Range: -10.7509
Max Act: 10.1884. Min Act: -0.1700
Data Index: 3738626 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7509. Min Range: -10.7509
Max Act: 10.2509. Min Act: -0.1700
Data Index: 4181591 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7509. Min Range: -10.7509
Max Act: 10.2509. Min Act: -0.1700
Data Index: 2222898 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7509. Min Range: -10.7509
Max Act: 10.2509. Min Act: -0.1700
Data Index: 5767538 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7509. Min Range: -10.7509
Max Act: 10.1884. Min Act: -0.1700
Data Index: 823344 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7509. Min Range: -10.7509
Max Act: 10.1259. Min Act: -0.1700
Data Index: 1612040 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7509. Min Range: -10.7509
Max Act: 10.1884. Min Act: -0.1700
Data Index: 4346716 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7509. Min Range: -10.7509
Max Act: 10.1884. Min Act: -0.1700
Data Index: 379090 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7509. Min Range: -10.7509
Max Act: 10.0634. Min Act: -0.1700
Data Index: 6737851 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7509. Min Range: -10.7509
Max Act: 10.0634. Min Act: -0.1700
Data Index: 3987720 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7509. Min Range: -10.7509
Max Act: 10.1259. Min Act: -0.1700
Data Index: 200296 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7509. Min Range: -10.7509
Max Act: 10.1259. Min Act: -0.1700
Data Index: 1766557 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19