Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6362 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9773. Min Range: -9.9773
Max Act: 9.9773. Min Act: -0.1700
Data Index: 5513984 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9773. Min Range: -9.9773
Max Act: 9.7898. Min Act: -0.1700
Data Index: 3014152 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9773. Min Range: -9.9773
Max Act: 9.7898. Min Act: -0.1700
Data Index: 7916123 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9773. Min Range: -9.9773
Max Act: 9.7898. Min Act: -0.1700
Data Index: 5232857 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9773. Min Range: -9.9773
Max Act: 9.6023. Min Act: -0.1700
Data Index: 3827256 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9773. Min Range: -9.9773
Max Act: 9.6023. Min Act: -0.1700
Data Index: 7393992 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9773. Min Range: -9.9773
Max Act: 9.5398. Min Act: -0.1700
Data Index: 122659 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9773. Min Range: -9.9773
Max Act: 9.5398. Min Act: -0.1700
Data Index: 7677621 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9773. Min Range: -9.9773
Max Act: 9.5398. Min Act: -0.1700
Data Index: 4132810 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9773. Min Range: -9.9773
Max Act: 9.5398. Min Act: -0.1700
Data Index: 3455451 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9773. Min Range: -9.9773
Max Act: 9.4148. Min Act: -0.1700
Data Index: 661112 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9773. Min Range: -9.9773
Max Act: 9.4148. Min Act: -0.1700
Data Index: 2915837 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9773. Min Range: -9.9773
Max Act: 9.3523. Min Act: -0.1700
Data Index: 3887216 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9773. Min Range: -9.9773
Max Act: 9.3523. Min Act: -0.1700
Data Index: 5844974 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9773. Min Range: -9.9773
Max Act: 9.3523. Min Act: -0.1700
Data Index: 1962585 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9773. Min Range: -9.9773
Max Act: 9.2898. Min Act: -0.1700
Data Index: 4854535 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9773. Min Range: -9.9773
Max Act: 9.2273. Min Act: -0.1700
Data Index: 7554920 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9773. Min Range: -9.9773
Max Act: 9.2273. Min Act: -0.1700
Data Index: 2788206 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9773. Min Range: -9.9773
Max Act: 9.2273. Min Act: -0.1700
Data Index: 4382944 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9773. Min Range: -9.9773
Max Act: 9.2273. Min Act: -0.1700
Data Index: 3116364 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19