Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2158 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.3398. Min Act: -0.1700
Data Index: 2965986 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.3086. Min Act: -0.1700
Data Index: 7109972 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.3086. Min Act: -0.1700
Data Index: 570941 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.3086. Min Act: -0.1700
Data Index: 3774151 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2773. Min Act: -0.1700
Data Index: 3719102 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2773. Min Act: -0.1700
Data Index: 7752709 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2773. Min Act: -0.1700
Data Index: 1365867 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2773. Min Act: -0.1700
Data Index: 6748879 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2773. Min Act: -0.1700
Data Index: 327197 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2461. Min Act: -0.1700
Data Index: 4622522 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2461. Min Act: -0.1700
Data Index: 1428069 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2461. Min Act: -0.1700
Data Index: 1760653 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2461. Min Act: -0.1700
Data Index: 4332977 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2461. Min Act: -0.1700
Data Index: 4165554 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2148. Min Act: -0.1700
Data Index: 6803020 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2148. Min Act: -0.1700
Data Index: 5129535 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2148. Min Act: -0.1700
Data Index: 7046098 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2148. Min Act: -0.1700
Data Index: 5869069 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2148. Min Act: -0.1700
Data Index: 6193777 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3398. Min Range: -4.3398
Max Act: 4.2148. Min Act: -0.1700
Data Index: 3977887 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19