Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1932. Min Range: -8.1932
Max Act: 8.1932. Min Act: -0.1700
Data Index: 5015388 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1932. Min Range: -8.1932
Max Act: 8.0682. Min Act: -0.1700
Data Index: 7278067 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1932. Min Range: -8.1932
Max Act: 8.0057. Min Act: -0.1700
Data Index: 7981820 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1932. Min Range: -8.1932
Max Act: 7.8807. Min Act: -0.1700
Data Index: 77565 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1932. Min Range: -8.1932
Max Act: 7.8182. Min Act: -0.1700
Data Index: 6601253 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1932. Min Range: -8.1932
Max Act: 7.7557. Min Act: -0.1700
Data Index: 5154114 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1932. Min Range: -8.1932
Max Act: 7.7557. Min Act: -0.1700
Data Index: 8045763 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1932. Min Range: -8.1932
Max Act: 7.7557. Min Act: -0.1700
Data Index: 4837879 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1932. Min Range: -8.1932
Max Act: 7.7557. Min Act: -0.1700
Data Index: 2205626 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1932. Min Range: -8.1932
Max Act: 7.7557. Min Act: -0.1700
Data Index: 5916430 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1932. Min Range: -8.1932
Max Act: 7.7557. Min Act: -0.1700
Data Index: 3385543 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1932. Min Range: -8.1932
Max Act: 7.6932. Min Act: -0.1700
Data Index: 4419803 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1932. Min Range: -8.1932
Max Act: 7.6932. Min Act: -0.1700
Data Index: 8510873 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1932. Min Range: -8.1932
Max Act: 7.6932. Min Act: -0.1700
Data Index: 4900097 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1932. Min Range: -8.1932
Max Act: 7.5995. Min Act: -0.1700
Data Index: 6578915 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1932. Min Range: -8.1932
Max Act: 7.5995. Min Act: -0.1700
Data Index: 517524 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1932. Min Range: -8.1932
Max Act: 7.5682. Min Act: -0.1700
Data Index: 8294134 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1932. Min Range: -8.1932
Max Act: 7.5682. Min Act: -0.1700
Data Index: 5283972 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1932. Min Range: -8.1932
Max Act: 7.5370. Min Act: -0.1700
Data Index: 7472888 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1932. Min Range: -8.1932
Max Act: 7.5370. Min Act: -0.1700
Data Index: 6672972 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19