Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3929 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9191. Min Range: -7.9191
Max Act: 7.9191. Min Act: -0.1700
Data Index: 8349223 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9191. Min Range: -7.9191
Max Act: 7.4816. Min Act: -0.1700
Data Index: 4386210 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9191. Min Range: -7.9191
Max Act: 7.3254. Min Act: -0.1700
Data Index: 867577 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9191. Min Range: -7.9191
Max Act: 7.3254. Min Act: -0.1700
Data Index: 1510839 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9191. Min Range: -7.9191
Max Act: 7.3254. Min Act: -0.1700
Data Index: 2313670 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9191. Min Range: -7.9191
Max Act: 7.2629. Min Act: -0.1700
Data Index: 8610965 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9191. Min Range: -7.9191
Max Act: 7.2316. Min Act: -0.1700
Data Index: 454658 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9191. Min Range: -7.9191
Max Act: 7.2316. Min Act: -0.1700
Data Index: 65880 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9191. Min Range: -7.9191
Max Act: 7.2004. Min Act: -0.1700
Data Index: 3338155 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9191. Min Range: -7.9191
Max Act: 7.2004. Min Act: -0.1700
Data Index: 600918 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9191. Min Range: -7.9191
Max Act: 7.1379. Min Act: -0.1700
Data Index: 1414585 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9191. Min Range: -7.9191
Max Act: 7.1066. Min Act: -0.1700
Data Index: 4074272 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9191. Min Range: -7.9191
Max Act: 7.1066. Min Act: -0.1700
Data Index: 6332282 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9191. Min Range: -7.9191
Max Act: 7.1066. Min Act: -0.1700
Data Index: 5668433 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9191. Min Range: -7.9191
Max Act: 7.1066. Min Act: -0.1700
Data Index: 6831849 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9191. Min Range: -7.9191
Max Act: 7.1066. Min Act: -0.1700
Data Index: 430 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9191. Min Range: -7.9191
Max Act: 7.1066. Min Act: -0.1700
Data Index: 8051726 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9191. Min Range: -7.9191
Max Act: 7.0129. Min Act: -0.1700
Data Index: 7244483 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9191. Min Range: -7.9191
Max Act: 7.0441. Min Act: -0.1700
Data Index: 4401165 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9191. Min Range: -7.9191
Max Act: 7.0129. Min Act: -0.1700
Data Index: 3243737 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19