Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2085 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9459. Min Range: -6.9459
Max Act: 6.9459. Min Act: -0.1700
Data Index: 7690991 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9459. Min Range: -6.9459
Max Act: 6.7896. Min Act: -0.1700
Data Index: 8730520 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9459. Min Range: -6.9459
Max Act: 6.7896. Min Act: -0.1700
Data Index: 61225 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9459. Min Range: -6.9459
Max Act: 6.7584. Min Act: -0.1700
Data Index: 8419403 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9459. Min Range: -6.9459
Max Act: 6.4771. Min Act: -0.1700
Data Index: 6229366 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9459. Min Range: -6.9459
Max Act: 6.4459. Min Act: -0.1700
Data Index: 749613 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9459. Min Range: -6.9459
Max Act: 6.4459. Min Act: -0.1700
Data Index: 7356949 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9459. Min Range: -6.9459
Max Act: 6.4146. Min Act: -0.1700
Data Index: 924582 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9459. Min Range: -6.9459
Max Act: 6.3834. Min Act: -0.1700
Data Index: 3848219 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9459. Min Range: -6.9459
Max Act: 6.3834. Min Act: -0.1700
Data Index: 1672413 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9459. Min Range: -6.9459
Max Act: 6.3834. Min Act: -0.1700
Data Index: 3804409 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9459. Min Range: -6.9459
Max Act: 6.3209. Min Act: -0.1700
Data Index: 6778090 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9459. Min Range: -6.9459
Max Act: 6.2896. Min Act: -0.1700
Data Index: 819017 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9459. Min Range: -6.9459
Max Act: 6.2896. Min Act: -0.1700
Data Index: 104713 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9459. Min Range: -6.9459
Max Act: 6.2271. Min Act: -0.1700
Data Index: 7217277 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9459. Min Range: -6.9459
Max Act: 6.2271. Min Act: -0.1700
Data Index: 5536697 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9459. Min Range: -6.9459
Max Act: 6.1959. Min Act: -0.1700
Data Index: 8690674 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9459. Min Range: -6.9459
Max Act: 6.1959. Min Act: -0.1700
Data Index: 5252194 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9459. Min Range: -6.9459
Max Act: 6.1646. Min Act: -0.1700
Data Index: 6409743 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9459. Min Range: -6.9459
Max Act: 6.1021. Min Act: -0.1700
Data Index: 7739728 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19