Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4825 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4969. Min Range: -6.4969
Max Act: 6.4969. Min Act: -0.1700
Data Index: 2400647 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4969. Min Range: -6.4969
Max Act: 6.4344. Min Act: -0.1700
Data Index: 2294081 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4969. Min Range: -6.4969
Max Act: 6.3094. Min Act: -0.1700
Data Index: 3860381 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4969. Min Range: -6.4969
Max Act: 6.3094. Min Act: -0.1700
Data Index: 3445858 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4969. Min Range: -6.4969
Max Act: 6.2781. Min Act: -0.1700
Data Index: 6465540 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4969. Min Range: -6.4969
Max Act: 6.2469. Min Act: -0.1700
Data Index: 5223429 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4969. Min Range: -6.4969
Max Act: 6.2469. Min Act: -0.1700
Data Index: 1551683 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4969. Min Range: -6.4969
Max Act: 6.2156. Min Act: -0.1700
Data Index: 8228853 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4969. Min Range: -6.4969
Max Act: 6.1844. Min Act: -0.1700
Data Index: 1351384 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4969. Min Range: -6.4969
Max Act: 6.1844. Min Act: -0.1700
Data Index: 7267306 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4969. Min Range: -6.4969
Max Act: 6.1844. Min Act: -0.1700
Data Index: 2874094 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4969. Min Range: -6.4969
Max Act: 6.1531. Min Act: -0.1700
Data Index: 83630 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4969. Min Range: -6.4969
Max Act: 6.1531. Min Act: -0.1700
Data Index: 8227066 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4969. Min Range: -6.4969
Max Act: 6.1219. Min Act: -0.1700
Data Index: 132246 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4969. Min Range: -6.4969
Max Act: 6.1531. Min Act: -0.1700
Data Index: 7027675 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4969. Min Range: -6.4969
Max Act: 6.0906. Min Act: -0.1700
Data Index: 2400636 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4969. Min Range: -6.4969
Max Act: 6.0906. Min Act: -0.1700
Data Index: 7542014 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4969. Min Range: -6.4969
Max Act: 6.0906. Min Act: -0.1700
Data Index: 1370363 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4969. Min Range: -6.4969
Max Act: 6.0906. Min Act: -0.1700
Data Index: 3648480 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4969. Min Range: -6.4969
Max Act: 6.0906. Min Act: -0.1700
Data Index: 6017703 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19