Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3982 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.3196. Min Act: -0.1700
Data Index: 354027 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.3196. Min Act: -0.1700
Data Index: 1451150 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.3196. Min Act: -0.1700
Data Index: 8096092 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.3196. Min Act: -0.1700
Data Index: 56429 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2882. Min Act: -0.1700
Data Index: 913884 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2882. Min Act: -0.1700
Data Index: 5128936 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2882. Min Act: -0.1700
Data Index: 2629893 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2882. Min Act: -0.1700
Data Index: 8599016 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2882. Min Act: -0.1700
Data Index: 438203 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2882. Min Act: -0.1700
Data Index: 3169019 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2882. Min Act: -0.1700
Data Index: 6470486 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2882. Min Act: -0.1700
Data Index: 1524196 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 7495658 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 1916885 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 6910676 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 4295248 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 4456725 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 8261279 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 6619729 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 4831652 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19