Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3855 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2596. Min Range: -7.2596
Max Act: 7.2596. Min Act: -0.1700
Data Index: 3034847 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2596. Min Range: -7.2596
Max Act: 7.1971. Min Act: -0.1700
Data Index: 2065203 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2596. Min Range: -7.2596
Max Act: 7.1034. Min Act: -0.1700
Data Index: 833268 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2596. Min Range: -7.2596
Max Act: 6.9159. Min Act: -0.1700
Data Index: 7546866 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2596. Min Range: -7.2596
Max Act: 6.8846. Min Act: -0.1700
Data Index: 5399089 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2596. Min Range: -7.2596
Max Act: 6.8846. Min Act: -0.1700
Data Index: 2103685 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2596. Min Range: -7.2596
Max Act: 6.8534. Min Act: -0.1700
Data Index: 6537181 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2596. Min Range: -7.2596
Max Act: 6.8221. Min Act: -0.1700
Data Index: 4527806 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2596. Min Range: -7.2596
Max Act: 6.8221. Min Act: -0.1700
Data Index: 372629 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2596. Min Range: -7.2596
Max Act: 6.7909. Min Act: -0.1700
Data Index: 2487388 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2596. Min Range: -7.2596
Max Act: 6.7909. Min Act: -0.1700
Data Index: 6874457 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2596. Min Range: -7.2596
Max Act: 6.8221. Min Act: -0.1700
Data Index: 5107697 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2596. Min Range: -7.2596
Max Act: 6.8221. Min Act: -0.1700
Data Index: 4296258 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2596. Min Range: -7.2596
Max Act: 6.7596. Min Act: -0.1700
Data Index: 2789939 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2596. Min Range: -7.2596
Max Act: 6.7596. Min Act: -0.1700
Data Index: 2911812 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2596. Min Range: -7.2596
Max Act: 6.7284. Min Act: -0.1700
Data Index: 8371549 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2596. Min Range: -7.2596
Max Act: 6.7284. Min Act: -0.1700
Data Index: 4884680 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2596. Min Range: -7.2596
Max Act: 6.7284. Min Act: -0.1700
Data Index: 7455482 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2596. Min Range: -7.2596
Max Act: 6.7284. Min Act: -0.1700
Data Index: 6752143 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2596. Min Range: -7.2596
Max Act: 6.6971. Min Act: -0.1700
Data Index: 5408913 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19