Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1826 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5804. Min Range: -8.5804
Max Act: 8.5804. Min Act: -0.1700
Data Index: 4898207 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5804. Min Range: -8.5804
Max Act: 8.5179. Min Act: -0.1700
Data Index: 4597563 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5804. Min Range: -8.5804
Max Act: 8.4554. Min Act: -0.1700
Data Index: 1630794 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5804. Min Range: -8.5804
Max Act: 8.3304. Min Act: -0.1700
Data Index: 4388504 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5804. Min Range: -8.5804
Max Act: 8.3304. Min Act: -0.1700
Data Index: 2884175 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5804. Min Range: -8.5804
Max Act: 8.3304. Min Act: -0.1700
Data Index: 3705432 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5804. Min Range: -8.5804
Max Act: 8.2054. Min Act: -0.1700
Data Index: 1193948 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5804. Min Range: -8.5804
Max Act: 8.2679. Min Act: -0.1700
Data Index: 185466 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5804. Min Range: -8.5804
Max Act: 8.1429. Min Act: -0.1700
Data Index: 2984478 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5804. Min Range: -8.5804
Max Act: 8.0804. Min Act: -0.1700
Data Index: 1804694 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5804. Min Range: -8.5804
Max Act: 8.0179. Min Act: -0.1700
Data Index: 4679469 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5804. Min Range: -8.5804
Max Act: 8.0179. Min Act: -0.1700
Data Index: 614324 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5804. Min Range: -8.5804
Max Act: 8.0179. Min Act: -0.1700
Data Index: 8666866 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5804. Min Range: -8.5804
Max Act: 8.0179. Min Act: -0.1700
Data Index: 2546560 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5804. Min Range: -8.5804
Max Act: 8.0179. Min Act: -0.1700
Data Index: 276905 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5804. Min Range: -8.5804
Max Act: 8.0179. Min Act: -0.1700
Data Index: 3182996 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5804. Min Range: -8.5804
Max Act: 7.9554. Min Act: -0.1700
Data Index: 6371532 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5804. Min Range: -8.5804
Max Act: 7.9554. Min Act: -0.1700
Data Index: 4170749 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5804. Min Range: -8.5804
Max Act: 7.9241. Min Act: -0.1700
Data Index: 7731876 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5804. Min Range: -8.5804
Max Act: 7.8929. Min Act: -0.1700
Data Index: 8705103 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19