Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 566 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1101. Min Range: -11.1101
Max Act: 11.1101. Min Act: -0.1699
Data Index: 5397781 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1101. Min Range: -11.1101
Max Act: 10.6101. Min Act: -0.1700
Data Index: 6716956 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1101. Min Range: -11.1101
Max Act: 10.6726. Min Act: -0.1700
Data Index: 5397780 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1101. Min Range: -11.1101
Max Act: 10.7351. Min Act: -0.1700
Data Index: 6008612 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1101. Min Range: -11.1101
Max Act: 10.6101. Min Act: -0.1700
Data Index: 5664430 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1101. Min Range: -11.1101
Max Act: 10.5476. Min Act: -0.1700
Data Index: 1355415 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1101. Min Range: -11.1101
Max Act: 10.4851. Min Act: -0.1699
Data Index: 7110390 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1101. Min Range: -11.1101
Max Act: 10.4226. Min Act: -0.1700
Data Index: 3189567 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1101. Min Range: -11.1101
Max Act: 10.3601. Min Act: -0.1700
Data Index: 7827302 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1101. Min Range: -11.1101
Max Act: 10.3601. Min Act: -0.1699
Data Index: 6127428 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1101. Min Range: -11.1101
Max Act: 10.4226. Min Act: -0.1700
Data Index: 8167680 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1101. Min Range: -11.1101
Max Act: 10.2976. Min Act: -0.1697
Data Index: 4010187 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1101. Min Range: -11.1101
Max Act: 10.2976. Min Act: -0.1700
Data Index: 8022321 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1101. Min Range: -11.1101
Max Act: 10.3601. Min Act: -0.1700
Data Index: 110387 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1101. Min Range: -11.1101
Max Act: 10.2976. Min Act: -0.1700
Data Index: 6102728 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1101. Min Range: -11.1101
Max Act: 10.3601. Min Act: -0.1700
Data Index: 4311317 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1101. Min Range: -11.1101
Max Act: 10.2351. Min Act: -0.1700
Data Index: 5158218 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1101. Min Range: -11.1101
Max Act: 10.2351. Min Act: -0.1700
Data Index: 3067002 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1101. Min Range: -11.1101
Max Act: 10.2351. Min Act: -0.1697
Data Index: 1836529 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1101. Min Range: -11.1101
Max Act: 10.2351. Min Act: -0.1700
Data Index: 2421550 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19