Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4222 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0242. Min Range: -6.0242
Max Act: 6.0242. Min Act: -0.1700
Data Index: 6656019 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0242. Min Range: -6.0242
Max Act: 5.9929. Min Act: -0.1700
Data Index: 8073809 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0242. Min Range: -6.0242
Max Act: 5.9617. Min Act: -0.1700
Data Index: 4406591 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0242. Min Range: -6.0242
Max Act: 5.9617. Min Act: -0.1700
Data Index: 1871768 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0242. Min Range: -6.0242
Max Act: 5.9304. Min Act: -0.1700
Data Index: 7692482 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0242. Min Range: -6.0242
Max Act: 5.9304. Min Act: -0.1700
Data Index: 1425327 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0242. Min Range: -6.0242
Max Act: 5.8367. Min Act: -0.1700
Data Index: 4571253 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0242. Min Range: -6.0242
Max Act: 5.8054. Min Act: -0.1700
Data Index: 3729091 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0242. Min Range: -6.0242
Max Act: 5.8054. Min Act: -0.1700
Data Index: 1941246 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0242. Min Range: -6.0242
Max Act: 5.8367. Min Act: -0.1700
Data Index: 5990420 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0242. Min Range: -6.0242
Max Act: 5.8054. Min Act: -0.1700
Data Index: 869746 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0242. Min Range: -6.0242
Max Act: 5.7742. Min Act: -0.1700
Data Index: 439785 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0242. Min Range: -6.0242
Max Act: 5.7742. Min Act: -0.1700
Data Index: 1941248 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0242. Min Range: -6.0242
Max Act: 5.7742. Min Act: -0.1700
Data Index: 222296 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0242. Min Range: -6.0242
Max Act: 5.7429. Min Act: -0.1700
Data Index: 6963855 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0242. Min Range: -6.0242
Max Act: 5.7429. Min Act: -0.1700
Data Index: 1553020 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0242. Min Range: -6.0242
Max Act: 5.7429. Min Act: -0.1700
Data Index: 6024122 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0242. Min Range: -6.0242
Max Act: 5.7117. Min Act: -0.1700
Data Index: 1935409 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0242. Min Range: -6.0242
Max Act: 5.7117. Min Act: -0.1700
Data Index: 4145591 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0242. Min Range: -6.0242
Max Act: 5.7117. Min Act: -0.1700
Data Index: 5547799 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19