Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2908 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1826. Min Range: -8.1826
Max Act: 8.1826. Min Act: -0.1700
Data Index: 519756 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1826. Min Range: -8.1826
Max Act: 7.7451. Min Act: -0.1700
Data Index: 1988097 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1826. Min Range: -8.1826
Max Act: 7.7139. Min Act: -0.1700
Data Index: 4018285 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1826. Min Range: -8.1826
Max Act: 7.5889. Min Act: -0.1700
Data Index: 8731492 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1826. Min Range: -8.1826
Max Act: 7.5264. Min Act: -0.1700
Data Index: 6432218 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1826. Min Range: -8.1826
Max Act: 7.4951. Min Act: -0.1700
Data Index: 4309328 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1826. Min Range: -8.1826
Max Act: 7.4326. Min Act: -0.1700
Data Index: 5915654 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1826. Min Range: -8.1826
Max Act: 7.4639. Min Act: -0.1700
Data Index: 1882416 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1826. Min Range: -8.1826
Max Act: 7.4326. Min Act: -0.1700
Data Index: 1652552 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1826. Min Range: -8.1826
Max Act: 7.3701. Min Act: -0.1700
Data Index: 734113 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1826. Min Range: -8.1826
Max Act: 7.3389. Min Act: -0.1700
Data Index: 7806480 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1826. Min Range: -8.1826
Max Act: 7.3076. Min Act: -0.1700
Data Index: 1864871 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1826. Min Range: -8.1826
Max Act: 7.2764. Min Act: -0.1700
Data Index: 3272038 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1826. Min Range: -8.1826
Max Act: 7.3076. Min Act: -0.1700
Data Index: 3765160 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1826. Min Range: -8.1826
Max Act: 7.2451. Min Act: -0.1700
Data Index: 6325729 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1826. Min Range: -8.1826
Max Act: 7.2139. Min Act: -0.1700
Data Index: 3134028 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1826. Min Range: -8.1826
Max Act: 7.2139. Min Act: -0.1700
Data Index: 5255071 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1826. Min Range: -8.1826
Max Act: 7.1514. Min Act: -0.1700
Data Index: 7222403 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1826. Min Range: -8.1826
Max Act: 7.1514. Min Act: -0.1700
Data Index: 7001351 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1826. Min Range: -8.1826
Max Act: 7.1514. Min Act: -0.1700
Data Index: 25296 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19