Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2403 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8322. Min Range: -5.8322
Max Act: 5.8322. Min Act: -0.1700
Data Index: 4494001 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8322. Min Range: -5.8322
Max Act: 5.6760. Min Act: -0.1700
Data Index: 2361691 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8322. Min Range: -5.8322
Max Act: 5.5510. Min Act: -0.1700
Data Index: 5838273 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8322. Min Range: -5.8322
Max Act: 5.4572. Min Act: -0.1700
Data Index: 356542 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8322. Min Range: -5.8322
Max Act: 5.4572. Min Act: -0.1700
Data Index: 4853449 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8322. Min Range: -5.8322
Max Act: 5.4572. Min Act: -0.1700
Data Index: 7786903 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8322. Min Range: -5.8322
Max Act: 5.4572. Min Act: -0.1700
Data Index: 660208 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8322. Min Range: -5.8322
Max Act: 5.4260. Min Act: -0.1700
Data Index: 8661859 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8322. Min Range: -5.8322
Max Act: 5.4260. Min Act: -0.1700
Data Index: 8032361 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8322. Min Range: -5.8322
Max Act: 5.3635. Min Act: -0.1700
Data Index: 6022166 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8322. Min Range: -5.8322
Max Act: 5.3635. Min Act: -0.1700
Data Index: 3616562 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8322. Min Range: -5.8322
Max Act: 5.3010. Min Act: -0.1700
Data Index: 8005906 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8322. Min Range: -5.8322
Max Act: 5.3635. Min Act: -0.1700
Data Index: 2978808 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8322. Min Range: -5.8322
Max Act: 5.3010. Min Act: -0.1700
Data Index: 2110854 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8322. Min Range: -5.8322
Max Act: 5.2385. Min Act: -0.1700
Data Index: 4788187 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8322. Min Range: -5.8322
Max Act: 5.2385. Min Act: -0.1700
Data Index: 7188280 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8322. Min Range: -5.8322
Max Act: 5.2072. Min Act: -0.1700
Data Index: 3740228 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8322. Min Range: -5.8322
Max Act: 5.2072. Min Act: -0.1700
Data Index: 1441271 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8322. Min Range: -5.8322
Max Act: 5.2072. Min Act: -0.1700
Data Index: 3124604 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8322. Min Range: -5.8322
Max Act: 5.2072. Min Act: -0.1700
Data Index: 111110 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19