Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.5442. Min Act: -0.1700
Data Index: 6015769 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.3880. Min Act: -0.1700
Data Index: 3839021 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.3567. Min Act: -0.1700
Data Index: 6859597 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.3255. Min Act: -0.1700
Data Index: 5644262 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.3255. Min Act: -0.1700
Data Index: 1700050 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.3255. Min Act: -0.1700
Data Index: 2036799 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.3255. Min Act: -0.1700
Data Index: 1827908 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.3255. Min Act: -0.1700
Data Index: 3236887 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.2942. Min Act: -0.1700
Data Index: 8042887 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.2942. Min Act: -0.1700
Data Index: 7412673 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.2630. Min Act: -0.1700
Data Index: 1803829 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.2317. Min Act: -0.1700
Data Index: 6662405 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.2630. Min Act: -0.1700
Data Index: 8269859 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.2630. Min Act: -0.1700
Data Index: 555004 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.2630. Min Act: -0.1700
Data Index: 2023924 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.2630. Min Act: -0.1700
Data Index: 3858314 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.2942. Min Act: -0.1700
Data Index: 3166229 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.2630. Min Act: -0.1700
Data Index: 3445290 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.2317. Min Act: -0.1700
Data Index: 1692072 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5442. Min Range: -4.5442
Max Act: 4.2317. Min Act: -0.1700
Data Index: 6614250 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19