Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4697 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.4287. Min Act: -0.1700
Data Index: 4534786 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.3349. Min Act: -0.1700
Data Index: 7238417 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.3349. Min Act: -0.1700
Data Index: 5150190 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.2724. Min Act: -0.1700
Data Index: 5207825 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.2412. Min Act: -0.1700
Data Index: 3583713 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.2099. Min Act: -0.1700
Data Index: 1354832 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.2099. Min Act: -0.1700
Data Index: 5174105 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.1474. Min Act: -0.1700
Data Index: 7621991 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.1162. Min Act: -0.1700
Data Index: 2367503 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.1162. Min Act: -0.1700
Data Index: 3658790 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.0849. Min Act: -0.1700
Data Index: 7760615 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.0849. Min Act: -0.1700
Data Index: 7608296 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.0849. Min Act: -0.1700
Data Index: 995498 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.0849. Min Act: -0.1700
Data Index: 4891021 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.0849. Min Act: -0.1700
Data Index: 5301804 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.0849. Min Act: -0.1700
Data Index: 6048762 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.0537. Min Act: -0.1700
Data Index: 8050599 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.0537. Min Act: -0.1700
Data Index: 7300647 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.0537. Min Act: -0.1700
Data Index: 2894066 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.0537. Min Act: -0.1700
Data Index: 4864399 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19