Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1074 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6379. Min Range: -4.6379
Max Act: 4.6379. Min Act: -0.1700
Data Index: 878326 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6379. Min Range: -4.6379
Max Act: 4.6066. Min Act: -0.1700
Data Index: 6440478 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6379. Min Range: -4.6379
Max Act: 4.6066. Min Act: -0.1700
Data Index: 4401036 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6379. Min Range: -4.6379
Max Act: 4.6066. Min Act: -0.1700
Data Index: 5150413 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6379. Min Range: -4.6379
Max Act: 4.5441. Min Act: -0.1700
Data Index: 9532 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6379. Min Range: -4.6379
Max Act: 4.5441. Min Act: -0.1700
Data Index: 5237430 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6379. Min Range: -4.6379
Max Act: 4.5441. Min Act: -0.1700
Data Index: 8810187 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6379. Min Range: -4.6379
Max Act: 4.5129. Min Act: -0.1700
Data Index: 6645522 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6379. Min Range: -4.6379
Max Act: 4.5129. Min Act: -0.1700
Data Index: 1652445 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6379. Min Range: -4.6379
Max Act: 4.4816. Min Act: -0.1700
Data Index: 2432458 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6379. Min Range: -4.6379
Max Act: 4.4816. Min Act: -0.1700
Data Index: 3553056 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6379. Min Range: -4.6379
Max Act: 4.4191. Min Act: -0.1700
Data Index: 4894061 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6379. Min Range: -4.6379
Max Act: 4.4504. Min Act: -0.1700
Data Index: 1520334 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6379. Min Range: -4.6379
Max Act: 4.4504. Min Act: -0.1700
Data Index: 2219551 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6379. Min Range: -4.6379
Max Act: 4.4504. Min Act: -0.1700
Data Index: 2250779 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6379. Min Range: -4.6379
Max Act: 4.4504. Min Act: -0.1700
Data Index: 6607294 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6379. Min Range: -4.6379
Max Act: 4.4504. Min Act: -0.1700
Data Index: 4040951 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6379. Min Range: -4.6379
Max Act: 4.4191. Min Act: -0.1700
Data Index: 2662001 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6379. Min Range: -4.6379
Max Act: 4.4191. Min Act: -0.1700
Data Index: 4211892 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6379. Min Range: -4.6379
Max Act: 4.4191. Min Act: -0.1700
Data Index: 6634572 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19