Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1333 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7324. Min Range: -5.7324
Max Act: 5.7324. Min Act: -0.1700
Data Index: 31047 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7324. Min Range: -5.7324
Max Act: 5.5761. Min Act: -0.1700
Data Index: 895984 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7324. Min Range: -5.7324
Max Act: 5.5136. Min Act: -0.1700
Data Index: 3028432 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7324. Min Range: -5.7324
Max Act: 5.4199. Min Act: -0.1700
Data Index: 8261772 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7324. Min Range: -5.7324
Max Act: 5.3261. Min Act: -0.1700
Data Index: 2644833 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7324. Min Range: -5.7324
Max Act: 5.3261. Min Act: -0.1700
Data Index: 6150345 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7324. Min Range: -5.7324
Max Act: 5.2949. Min Act: -0.1700
Data Index: 232983 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7324. Min Range: -5.7324
Max Act: 5.3261. Min Act: -0.1700
Data Index: 5340421 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7324. Min Range: -5.7324
Max Act: 5.2949. Min Act: -0.1700
Data Index: 4229964 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7324. Min Range: -5.7324
Max Act: 5.2636. Min Act: -0.1700
Data Index: 5626133 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7324. Min Range: -5.7324
Max Act: 5.2636. Min Act: -0.1700
Data Index: 8068620 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7324. Min Range: -5.7324
Max Act: 5.2324. Min Act: -0.1700
Data Index: 6610261 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7324. Min Range: -5.7324
Max Act: 5.2324. Min Act: -0.1700
Data Index: 5643669 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7324. Min Range: -5.7324
Max Act: 5.2011. Min Act: -0.1700
Data Index: 8419472 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7324. Min Range: -5.7324
Max Act: 5.2324. Min Act: -0.1700
Data Index: 7227439 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7324. Min Range: -5.7324
Max Act: 5.1699. Min Act: -0.1700
Data Index: 818991 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7324. Min Range: -5.7324
Max Act: 5.2636. Min Act: -0.1700
Data Index: 2714834 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7324. Min Range: -5.7324
Max Act: 5.1699. Min Act: -0.1700
Data Index: 6943285 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7324. Min Range: -5.7324
Max Act: 5.1386. Min Act: -0.1700
Data Index: 1965406 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7324. Min Range: -5.7324
Max Act: 5.1074. Min Act: -0.1700
Data Index: 4588034 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19