Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2962 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7114. Min Range: -6.7114
Max Act: 6.7114. Min Act: -0.1700
Data Index: 8753391 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7114. Min Range: -6.7114
Max Act: 6.7114. Min Act: -0.1700
Data Index: 4118010 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7114. Min Range: -6.7114
Max Act: 6.6177. Min Act: -0.1700
Data Index: 8007833 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7114. Min Range: -6.7114
Max Act: 6.6177. Min Act: -0.1700
Data Index: 1317350 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7114. Min Range: -6.7114
Max Act: 6.5239. Min Act: -0.1700
Data Index: 6742311 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7114. Min Range: -6.7114
Max Act: 6.5239. Min Act: -0.1700
Data Index: 4118009 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7114. Min Range: -6.7114
Max Act: 6.4927. Min Act: -0.1700
Data Index: 2440585 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7114. Min Range: -6.7114
Max Act: 6.3989. Min Act: -0.1700
Data Index: 6643914 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7114. Min Range: -6.7114
Max Act: 6.3989. Min Act: -0.1700
Data Index: 8343527 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7114. Min Range: -6.7114
Max Act: 6.3677. Min Act: -0.1700
Data Index: 500105 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7114. Min Range: -6.7114
Max Act: 6.3677. Min Act: -0.1700
Data Index: 7588033 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7114. Min Range: -6.7114
Max Act: 6.3677. Min Act: -0.1700
Data Index: 1821628 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7114. Min Range: -6.7114
Max Act: 6.3364. Min Act: -0.1700
Data Index: 3696247 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7114. Min Range: -6.7114
Max Act: 6.3364. Min Act: -0.1700
Data Index: 6936377 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7114. Min Range: -6.7114
Max Act: 6.3364. Min Act: -0.1700
Data Index: 1064659 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7114. Min Range: -6.7114
Max Act: 6.3364. Min Act: -0.1700
Data Index: 5242398 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7114. Min Range: -6.7114
Max Act: 6.2739. Min Act: -0.1700
Data Index: 7852189 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7114. Min Range: -6.7114
Max Act: 6.3052. Min Act: -0.1700
Data Index: 7887633 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7114. Min Range: -6.7114
Max Act: 6.3052. Min Act: -0.1700
Data Index: 5159555 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7114. Min Range: -6.7114
Max Act: 6.3052. Min Act: -0.1700
Data Index: 2843664 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19