Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3426 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.9207. Min Act: -0.1700
Data Index: 1815821 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.7957. Min Act: -0.1700
Data Index: 6722781 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.7019. Min Act: -0.1700
Data Index: 6536218 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.7019. Min Act: -0.1700
Data Index: 8134404 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.6394. Min Act: -0.1700
Data Index: 6231457 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.6394. Min Act: -0.1700
Data Index: 1890542 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.6082. Min Act: -0.1700
Data Index: 897666 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.6082. Min Act: -0.1700
Data Index: 3700556 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.5769. Min Act: -0.1700
Data Index: 3198445 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.5457. Min Act: -0.1700
Data Index: 6777988 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.5457. Min Act: -0.1700
Data Index: 5675873 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.5144. Min Act: -0.1700
Data Index: 3150594 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.5144. Min Act: -0.1700
Data Index: 7520324 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.5144. Min Act: -0.1700
Data Index: 3705922 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.5457. Min Act: -0.1700
Data Index: 3785847 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.5144. Min Act: -0.1700
Data Index: 2361308 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.4832. Min Act: -0.1700
Data Index: 4860672 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.5144. Min Act: -0.1700
Data Index: 6217494 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.4832. Min Act: -0.1700
Data Index: 4056380 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.4832. Min Act: -0.1700
Data Index: 3504076 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19