Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3767 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9167. Min Range: -5.9167
Max Act: 5.9167. Min Act: -0.1700
Data Index: 722834 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9167. Min Range: -5.9167
Max Act: 5.6355. Min Act: -0.1700
Data Index: 4056658 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9167. Min Range: -5.9167
Max Act: 5.5417. Min Act: -0.1700
Data Index: 6869260 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9167. Min Range: -5.9167
Max Act: 5.5417. Min Act: -0.1700
Data Index: 7974656 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9167. Min Range: -5.9167
Max Act: 5.5105. Min Act: -0.1700
Data Index: 2782514 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9167. Min Range: -5.9167
Max Act: 5.3855. Min Act: -0.1700
Data Index: 3072670 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9167. Min Range: -5.9167
Max Act: 5.3855. Min Act: -0.1700
Data Index: 5463010 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9167. Min Range: -5.9167
Max Act: 5.4167. Min Act: -0.1700
Data Index: 7112549 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9167. Min Range: -5.9167
Max Act: 5.3542. Min Act: -0.1700
Data Index: 3884161 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9167. Min Range: -5.9167
Max Act: 5.3230. Min Act: -0.1700
Data Index: 1183357 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9167. Min Range: -5.9167
Max Act: 5.3230. Min Act: -0.1700
Data Index: 2229325 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9167. Min Range: -5.9167
Max Act: 5.3542. Min Act: -0.1700
Data Index: 7673099 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9167. Min Range: -5.9167
Max Act: 5.3230. Min Act: -0.1700
Data Index: 5952869 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9167. Min Range: -5.9167
Max Act: 5.2605. Min Act: -0.1700
Data Index: 1510281 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9167. Min Range: -5.9167
Max Act: 5.2605. Min Act: -0.1700
Data Index: 751133 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9167. Min Range: -5.9167
Max Act: 5.2605. Min Act: -0.1700
Data Index: 8798066 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9167. Min Range: -5.9167
Max Act: 5.2605. Min Act: -0.1700
Data Index: 2413559 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9167. Min Range: -5.9167
Max Act: 5.2292. Min Act: -0.1700
Data Index: 4208327 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9167. Min Range: -5.9167
Max Act: 5.2292. Min Act: -0.1700
Data Index: 352242 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9167. Min Range: -5.9167
Max Act: 5.1667. Min Act: -0.1700
Data Index: 2431411 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19