Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5173 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9344. Min Range: -8.9344
Max Act: 8.9344. Min Act: -0.1700
Data Index: 6273188 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9344. Min Range: -8.9344
Max Act: 8.6219. Min Act: -0.1700
Data Index: 6046338 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9344. Min Range: -8.9344
Max Act: 8.4969. Min Act: -0.1700
Data Index: 4631195 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9344. Min Range: -8.9344
Max Act: 8.3719. Min Act: -0.1700
Data Index: 7865234 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9344. Min Range: -8.9344
Max Act: 8.3094. Min Act: -0.1700
Data Index: 2442679 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9344. Min Range: -8.9344
Max Act: 8.3094. Min Act: -0.1700
Data Index: 7567575 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9344. Min Range: -8.9344
Max Act: 8.3094. Min Act: -0.1700
Data Index: 507536 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9344. Min Range: -8.9344
Max Act: 8.2469. Min Act: -0.1700
Data Index: 8664051 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9344. Min Range: -8.9344
Max Act: 8.2469. Min Act: -0.1700
Data Index: 6351619 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9344. Min Range: -8.9344
Max Act: 8.2469. Min Act: -0.1700
Data Index: 2969471 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9344. Min Range: -8.9344
Max Act: 8.2469. Min Act: -0.1700
Data Index: 8665923 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9344. Min Range: -8.9344
Max Act: 8.2469. Min Act: -0.1700
Data Index: 3980603 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9344. Min Range: -8.9344
Max Act: 8.2469. Min Act: -0.1700
Data Index: 8174386 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9344. Min Range: -8.9344
Max Act: 8.1844. Min Act: -0.1700
Data Index: 984605 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9344. Min Range: -8.9344
Max Act: 8.1844. Min Act: -0.1700
Data Index: 6377779 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9344. Min Range: -8.9344
Max Act: 8.1844. Min Act: -0.1700
Data Index: 8818200 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9344. Min Range: -8.9344
Max Act: 8.1844. Min Act: -0.1700
Data Index: 814959 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9344. Min Range: -8.9344
Max Act: 8.1219. Min Act: -0.1700
Data Index: 5560920 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9344. Min Range: -8.9344
Max Act: 8.1219. Min Act: -0.1700
Data Index: 1730130 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9344. Min Range: -8.9344
Max Act: 8.1219. Min Act: -0.1700
Data Index: 7371256 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19