Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4776 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9961. Min Range: -4.9961
Max Act: 4.9961. Min Act: -0.1700
Data Index: 5333963 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9961. Min Range: -4.9961
Max Act: 4.8399. Min Act: -0.1700
Data Index: 4618378 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9961. Min Range: -4.9961
Max Act: 4.7774. Min Act: -0.1700
Data Index: 1151112 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9961. Min Range: -4.9961
Max Act: 4.7774. Min Act: -0.1700
Data Index: 8105807 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9961. Min Range: -4.9961
Max Act: 4.7461. Min Act: -0.1700
Data Index: 879917 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9961. Min Range: -4.9961
Max Act: 4.7461. Min Act: -0.1700
Data Index: 3446723 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9961. Min Range: -4.9961
Max Act: 4.6836. Min Act: -0.1700
Data Index: 5286644 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9961. Min Range: -4.9961
Max Act: 4.6836. Min Act: -0.1700
Data Index: 7300393 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9961. Min Range: -4.9961
Max Act: 4.5899. Min Act: -0.1700
Data Index: 3761510 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9961. Min Range: -4.9961
Max Act: 4.6211. Min Act: -0.1700
Data Index: 5766850 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9961. Min Range: -4.9961
Max Act: 4.5899. Min Act: -0.1700
Data Index: 8826942 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9961. Min Range: -4.9961
Max Act: 4.5586. Min Act: -0.1700
Data Index: 5749293 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9961. Min Range: -4.9961
Max Act: 4.5586. Min Act: -0.1700
Data Index: 5303383 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9961. Min Range: -4.9961
Max Act: 4.5274. Min Act: -0.1700
Data Index: 594377 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9961. Min Range: -4.9961
Max Act: 4.4961. Min Act: -0.1700
Data Index: 219239 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9961. Min Range: -4.9961
Max Act: 4.5274. Min Act: -0.1700
Data Index: 2253438 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9961. Min Range: -4.9961
Max Act: 4.5274. Min Act: -0.1700
Data Index: 7527885 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9961. Min Range: -4.9961
Max Act: 4.4961. Min Act: -0.1700
Data Index: 3079475 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9961. Min Range: -4.9961
Max Act: 4.5274. Min Act: -0.1700
Data Index: 2806065 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9961. Min Range: -4.9961
Max Act: 4.4961. Min Act: -0.1700
Data Index: 6106918 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19