Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3905 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8898. Min Range: -10.8898
Max Act: 10.8898. Min Act: -0.1700
Data Index: 7520544 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8898. Min Range: -10.8898
Max Act: 10.8273. Min Act: -0.1700
Data Index: 6631177 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8898. Min Range: -10.8898
Max Act: 10.7648. Min Act: -0.1700
Data Index: 3184788 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8898. Min Range: -10.8898
Max Act: 10.1398. Min Act: -0.1700
Data Index: 1186821 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8898. Min Range: -10.8898
Max Act: 10.2023. Min Act: -0.1700
Data Index: 4458679 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8898. Min Range: -10.8898
Max Act: 9.8273. Min Act: -0.1700
Data Index: 4629649 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8898. Min Range: -10.8898
Max Act: 9.7648. Min Act: -0.1700
Data Index: 8667615 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8898. Min Range: -10.8898
Max Act: 9.5148. Min Act: -0.1700
Data Index: 6997987 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8898. Min Range: -10.8898
Max Act: 9.5148. Min Act: -0.1700
Data Index: 3290855 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8898. Min Range: -10.8898
Max Act: 9.5148. Min Act: -0.1700
Data Index: 7232147 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8898. Min Range: -10.8898
Max Act: 9.5148. Min Act: -0.1700
Data Index: 1648108 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8898. Min Range: -10.8898
Max Act: 9.4523. Min Act: -0.1700
Data Index: 1374909 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8898. Min Range: -10.8898
Max Act: 9.3898. Min Act: -0.1700
Data Index: 2469110 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8898. Min Range: -10.8898
Max Act: 9.3898. Min Act: -0.1700
Data Index: 7329117 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8898. Min Range: -10.8898
Max Act: 9.3898. Min Act: -0.1700
Data Index: 5579386 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8898. Min Range: -10.8898
Max Act: 9.3898. Min Act: -0.1700
Data Index: 560645 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8898. Min Range: -10.8898
Max Act: 9.3898. Min Act: -0.1700
Data Index: 3412181 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8898. Min Range: -10.8898
Max Act: 9.3273. Min Act: -0.1700
Data Index: 1990791 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8898. Min Range: -10.8898
Max Act: 9.3273. Min Act: -0.1700
Data Index: 8439193 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8898. Min Range: -10.8898
Max Act: 9.3273. Min Act: -0.1700
Data Index: 3866382 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19