Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5141 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.4766. Min Act: -0.1700
Data Index: 4351766 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.4454. Min Act: -0.1700
Data Index: 6060003 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.3516. Min Act: -0.1700
Data Index: 3783527 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.3204. Min Act: -0.1700
Data Index: 2922517 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.2579. Min Act: -0.1700
Data Index: 1894921 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.1954. Min Act: -0.1700
Data Index: 5542559 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.2266. Min Act: -0.1700
Data Index: 2154234 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.1954. Min Act: -0.1700
Data Index: 3328775 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.1954. Min Act: -0.1700
Data Index: 893586 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.1329. Min Act: -0.1700
Data Index: 8487941 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.1016. Min Act: -0.1700
Data Index: 6042685 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.1016. Min Act: -0.1700
Data Index: 7510647 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.0704. Min Act: -0.1700
Data Index: 920510 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.1016. Min Act: -0.1700
Data Index: 1970183 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.0704. Min Act: -0.1700
Data Index: 5583674 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.0704. Min Act: -0.1700
Data Index: 131303 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.0704. Min Act: -0.1700
Data Index: 7048720 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.0704. Min Act: -0.1700
Data Index: 7244487 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.0391. Min Act: -0.1700
Data Index: 4024098 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4766. Min Range: -7.4766
Max Act: 6.9766. Min Act: -0.1700
Data Index: 2501853 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19