Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4756 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0966. Min Range: -5.0966
Max Act: 5.0966. Min Act: -0.1700
Data Index: 3721730 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0966. Min Range: -5.0966
Max Act: 5.0966. Min Act: -0.1700
Data Index: 3276216 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0966. Min Range: -5.0966
Max Act: 5.0341. Min Act: -0.1700
Data Index: 790329 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0966. Min Range: -5.0966
Max Act: 5.0653. Min Act: -0.1700
Data Index: 582441 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0966. Min Range: -5.0966
Max Act: 5.0341. Min Act: -0.1700
Data Index: 6798225 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0966. Min Range: -5.0966
Max Act: 5.0028. Min Act: -0.1700
Data Index: 6484730 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0966. Min Range: -5.0966
Max Act: 4.9403. Min Act: -0.1700
Data Index: 6392696 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0966. Min Range: -5.0966
Max Act: 4.9091. Min Act: -0.1700
Data Index: 1528058 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0966. Min Range: -5.0966
Max Act: 4.9091. Min Act: -0.1700
Data Index: 5793328 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0966. Min Range: -5.0966
Max Act: 4.8778. Min Act: -0.1700
Data Index: 3351917 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0966. Min Range: -5.0966
Max Act: 4.8466. Min Act: -0.1700
Data Index: 7959468 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0966. Min Range: -5.0966
Max Act: 4.8466. Min Act: -0.1700
Data Index: 8409285 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0966. Min Range: -5.0966
Max Act: 4.8466. Min Act: -0.1700
Data Index: 6333875 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0966. Min Range: -5.0966
Max Act: 4.8153. Min Act: -0.1700
Data Index: 7708386 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0966. Min Range: -5.0966
Max Act: 4.8153. Min Act: -0.1700
Data Index: 2871197 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0966. Min Range: -5.0966
Max Act: 4.8153. Min Act: -0.1700
Data Index: 1170652 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0966. Min Range: -5.0966
Max Act: 4.8153. Min Act: -0.1700
Data Index: 3595810 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0966. Min Range: -5.0966
Max Act: 4.7841. Min Act: -0.1700
Data Index: 5864276 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0966. Min Range: -5.0966
Max Act: 4.8153. Min Act: -0.1700
Data Index: 3752332 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0966. Min Range: -5.0966
Max Act: 4.7841. Min Act: -0.1700
Data Index: 5361307 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19