Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2766 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6038. Min Range: -4.6038
Max Act: 4.6038. Min Act: -0.1700
Data Index: 1703761 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6038. Min Range: -4.6038
Max Act: 4.5726. Min Act: -0.1700
Data Index: 1383569 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6038. Min Range: -4.6038
Max Act: 4.5101. Min Act: -0.1700
Data Index: 788715 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6038. Min Range: -4.6038
Max Act: 4.4163. Min Act: -0.1700
Data Index: 6481725 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6038. Min Range: -4.6038
Max Act: 4.3851. Min Act: -0.1700
Data Index: 7609988 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6038. Min Range: -4.6038
Max Act: 4.4163. Min Act: -0.1700
Data Index: 3066551 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6038. Min Range: -4.6038
Max Act: 4.3851. Min Act: -0.1700
Data Index: 6325531 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6038. Min Range: -4.6038
Max Act: 4.4163. Min Act: -0.1700
Data Index: 3066552 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6038. Min Range: -4.6038
Max Act: 4.3538. Min Act: -0.1700
Data Index: 4349165 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6038. Min Range: -4.6038
Max Act: 4.3538. Min Act: -0.1700
Data Index: 6218531 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6038. Min Range: -4.6038
Max Act: 4.3226. Min Act: -0.1700
Data Index: 8120785 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6038. Min Range: -4.6038
Max Act: 4.3226. Min Act: -0.1700
Data Index: 3406158 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6038. Min Range: -4.6038
Max Act: 4.3226. Min Act: -0.1700
Data Index: 7666010 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6038. Min Range: -4.6038
Max Act: 4.2601. Min Act: -0.1700
Data Index: 883911 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6038. Min Range: -4.6038
Max Act: 4.2913. Min Act: -0.1700
Data Index: 7065552 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6038. Min Range: -4.6038
Max Act: 4.2913. Min Act: -0.1700
Data Index: 5211682 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6038. Min Range: -4.6038
Max Act: 4.2913. Min Act: -0.1700
Data Index: 5024323 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6038. Min Range: -4.6038
Max Act: 4.2601. Min Act: -0.1700
Data Index: 7808431 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6038. Min Range: -4.6038
Max Act: 4.2288. Min Act: -0.1700
Data Index: 2713313 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6038. Min Range: -4.6038
Max Act: 4.2601. Min Act: -0.1700
Data Index: 4683398 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19