Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3630 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7460. Min Range: -7.7460
Max Act: 7.7460. Min Act: -0.1700
Data Index: 4001121 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7460. Min Range: -7.7460
Max Act: 7.6523. Min Act: -0.1700
Data Index: 6605750 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7460. Min Range: -7.7460
Max Act: 7.6523. Min Act: -0.1700
Data Index: 3136184 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7460. Min Range: -7.7460
Max Act: 7.5898. Min Act: -0.1700
Data Index: 8157725 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7460. Min Range: -7.7460
Max Act: 7.5585. Min Act: -0.1700
Data Index: 7895009 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7460. Min Range: -7.7460
Max Act: 7.5273. Min Act: -0.1700
Data Index: 8573143 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7460. Min Range: -7.7460
Max Act: 7.4335. Min Act: -0.1700
Data Index: 6121159 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7460. Min Range: -7.7460
Max Act: 7.4023. Min Act: -0.1700
Data Index: 7149693 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7460. Min Range: -7.7460
Max Act: 7.4023. Min Act: -0.1700
Data Index: 6194415 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7460. Min Range: -7.7460
Max Act: 7.3710. Min Act: -0.1700
Data Index: 6128850 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7460. Min Range: -7.7460
Max Act: 7.3710. Min Act: -0.1700
Data Index: 2605670 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7460. Min Range: -7.7460
Max Act: 7.4023. Min Act: -0.1700
Data Index: 4318388 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7460. Min Range: -7.7460
Max Act: 7.3398. Min Act: -0.1700
Data Index: 3907973 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7460. Min Range: -7.7460
Max Act: 7.3398. Min Act: -0.1700
Data Index: 8271565 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7460. Min Range: -7.7460
Max Act: 7.3085. Min Act: -0.1700
Data Index: 2626296 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7460. Min Range: -7.7460
Max Act: 7.2773. Min Act: -0.1700
Data Index: 2086073 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7460. Min Range: -7.7460
Max Act: 7.2773. Min Act: -0.1700
Data Index: 2811709 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7460. Min Range: -7.7460
Max Act: 7.2773. Min Act: -0.1700
Data Index: 8813672 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7460. Min Range: -7.7460
Max Act: 7.2773. Min Act: -0.1700
Data Index: 6450688 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7460. Min Range: -7.7460
Max Act: 7.2460. Min Act: -0.1700
Data Index: 6126868 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19