Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 14 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6296. Min Range: -6.6296
Max Act: 6.6296. Min Act: -0.1700
Data Index: 7355114 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6296. Min Range: -6.6296
Max Act: 6.5984. Min Act: -0.1700
Data Index: 5462731 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6296. Min Range: -6.6296
Max Act: 6.5671. Min Act: -0.1700
Data Index: 3986395 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6296. Min Range: -6.6296
Max Act: 6.5671. Min Act: -0.1700
Data Index: 1758476 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6296. Min Range: -6.6296
Max Act: 6.5671. Min Act: -0.1700
Data Index: 2169139 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6296. Min Range: -6.6296
Max Act: 6.5359. Min Act: -0.1700
Data Index: 505979 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6296. Min Range: -6.6296
Max Act: 6.5046. Min Act: -0.1700
Data Index: 8722497 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6296. Min Range: -6.6296
Max Act: 6.4734. Min Act: -0.1700
Data Index: 7693160 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6296. Min Range: -6.6296
Max Act: 6.5046. Min Act: -0.1700
Data Index: 3306564 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6296. Min Range: -6.6296
Max Act: 6.4734. Min Act: -0.1700
Data Index: 6392805 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6296. Min Range: -6.6296
Max Act: 6.4421. Min Act: -0.1700
Data Index: 11544 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6296. Min Range: -6.6296
Max Act: 6.4421. Min Act: -0.1700
Data Index: 6992465 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6296. Min Range: -6.6296
Max Act: 6.4109. Min Act: -0.1700
Data Index: 7552011 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6296. Min Range: -6.6296
Max Act: 6.4421. Min Act: -0.1700
Data Index: 6149197 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6296. Min Range: -6.6296
Max Act: 6.3796. Min Act: -0.1700
Data Index: 6755557 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6296. Min Range: -6.6296
Max Act: 6.3484. Min Act: -0.1700
Data Index: 6390402 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6296. Min Range: -6.6296
Max Act: 6.3796. Min Act: -0.1700
Data Index: 7861868 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6296. Min Range: -6.6296
Max Act: 6.3484. Min Act: -0.1700
Data Index: 6879007 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6296. Min Range: -6.6296
Max Act: 6.3171. Min Act: -0.1700
Data Index: 4349807 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6296. Min Range: -6.6296
Max Act: 6.3484. Min Act: -0.1700
Data Index: 4753475 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19