Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2566 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7941. Min Range: -3.7941
Max Act: 3.7941. Min Act: -0.1700
Data Index: 8350848 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7941. Min Range: -3.7941
Max Act: 3.7941. Min Act: -0.1700
Data Index: 6830771 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7941. Min Range: -3.7941
Max Act: 3.7628. Min Act: -0.1700
Data Index: 2011963 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7941. Min Range: -3.7941
Max Act: 3.7628. Min Act: -0.1700
Data Index: 1364306 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7941. Min Range: -3.7941
Max Act: 3.7315. Min Act: -0.1700
Data Index: 7919037 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7941. Min Range: -3.7941
Max Act: 3.7002. Min Act: -0.1700
Data Index: 3283007 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7941. Min Range: -3.7941
Max Act: 3.7002. Min Act: -0.1700
Data Index: 6527642 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7941. Min Range: -3.7941
Max Act: 3.7002. Min Act: -0.1700
Data Index: 5095651 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7941. Min Range: -3.7941
Max Act: 3.6689. Min Act: -0.1700
Data Index: 831431 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7941. Min Range: -3.7941
Max Act: 3.6689. Min Act: -0.1700
Data Index: 8368406 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7941. Min Range: -3.7941
Max Act: 3.6689. Min Act: -0.1700
Data Index: 6058195 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7941. Min Range: -3.7941
Max Act: 3.6689. Min Act: -0.1700
Data Index: 5720313 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7941. Min Range: -3.7941
Max Act: 3.6689. Min Act: -0.1700
Data Index: 7331738 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7941. Min Range: -3.7941
Max Act: 3.6376. Min Act: -0.1700
Data Index: 8061585 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7941. Min Range: -3.7941
Max Act: 3.6064. Min Act: -0.1700
Data Index: 8617998 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7941. Min Range: -3.7941
Max Act: 3.6064. Min Act: -0.1700
Data Index: 3925383 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7941. Min Range: -3.7941
Max Act: 3.6376. Min Act: -0.1700
Data Index: 8624299 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7941. Min Range: -3.7941
Max Act: 3.6064. Min Act: -0.1700
Data Index: 5606931 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7941. Min Range: -3.7941
Max Act: 3.5750. Min Act: -0.1700
Data Index: 3740532 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7941. Min Range: -3.7941
Max Act: 3.5750. Min Act: -0.1700
Data Index: 4951109 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19