Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1570 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3358. Min Range: -6.3358
Max Act: 6.3358. Min Act: -0.1700
Data Index: 8145207 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3358. Min Range: -6.3358
Max Act: 6.2420. Min Act: -0.1700
Data Index: 541765 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3358. Min Range: -6.3358
Max Act: 6.1170. Min Act: -0.1700
Data Index: 7673745 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3358. Min Range: -6.3358
Max Act: 6.1170. Min Act: -0.1700
Data Index: 7673746 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3358. Min Range: -6.3358
Max Act: 6.1170. Min Act: -0.1700
Data Index: 4219267 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3358. Min Range: -6.3358
Max Act: 6.0858. Min Act: -0.1700
Data Index: 5803545 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3358. Min Range: -6.3358
Max Act: 6.0545. Min Act: -0.1700
Data Index: 7673744 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3358. Min Range: -6.3358
Max Act: 6.0233. Min Act: -0.1700
Data Index: 3919529 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3358. Min Range: -6.3358
Max Act: 5.7733. Min Act: -0.1700
Data Index: 5610147 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3358. Min Range: -6.3358
Max Act: 5.6170. Min Act: -0.1700
Data Index: 5193323 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3358. Min Range: -6.3358
Max Act: 5.5858. Min Act: -0.1700
Data Index: 4871338 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3358. Min Range: -6.3358
Max Act: 5.5233. Min Act: -0.1700
Data Index: 4999524 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3358. Min Range: -6.3358
Max Act: 5.4920. Min Act: -0.1700
Data Index: 357856 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3358. Min Range: -6.3358
Max Act: 5.4608. Min Act: -0.1700
Data Index: 5995192 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3358. Min Range: -6.3358
Max Act: 5.3983. Min Act: -0.1700
Data Index: 7190320 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3358. Min Range: -6.3358
Max Act: 5.3983. Min Act: -0.1700
Data Index: 1530768 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3358. Min Range: -6.3358
Max Act: 5.3358. Min Act: -0.1700
Data Index: 8011336 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3358. Min Range: -6.3358
Max Act: 5.3670. Min Act: -0.1700
Data Index: 1288115 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3358. Min Range: -6.3358
Max Act: 5.3358. Min Act: -0.1700
Data Index: 7508039 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3358. Min Range: -6.3358
Max Act: 5.3670. Min Act: -0.1700
Data Index: 944202 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19