Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2444 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.7320. Min Act: -0.1700
Data Index: 2882111 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.7007. Min Act: -0.1700
Data Index: 5158154 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.6382. Min Act: -0.1700
Data Index: 7860043 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.6695. Min Act: -0.1700
Data Index: 5575370 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.6382. Min Act: -0.1700
Data Index: 1257979 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.6382. Min Act: -0.1700
Data Index: 2226277 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.6070. Min Act: -0.1700
Data Index: 3539427 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.6382. Min Act: -0.1700
Data Index: 4721671 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.6070. Min Act: -0.1700
Data Index: 6846292 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.5757. Min Act: -0.1700
Data Index: 3315648 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.5757. Min Act: -0.1700
Data Index: 858356 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.5757. Min Act: -0.1700
Data Index: 5760814 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.5757. Min Act: -0.1700
Data Index: 8788061 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.5757. Min Act: -0.1700
Data Index: 727317 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.5757. Min Act: -0.1700
Data Index: 2173656 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.5757. Min Act: -0.1700
Data Index: 4013518 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.5132. Min Act: -0.1700
Data Index: 2684063 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.5445. Min Act: -0.1700
Data Index: 2846860 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.5445. Min Act: -0.1700
Data Index: 479566 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.5132. Min Act: -0.1700
Data Index: 6356983 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19