Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3335 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8173. Min Range: -8.8173
Max Act: 8.8173. Min Act: -0.1700
Data Index: 8597603 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8173. Min Range: -8.8173
Max Act: 8.6923. Min Act: -0.1700
Data Index: 5405137 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8173. Min Range: -8.8173
Max Act: 8.5673. Min Act: -0.1700
Data Index: 7624752 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8173. Min Range: -8.8173
Max Act: 8.5048. Min Act: -0.1700
Data Index: 2808685 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8173. Min Range: -8.8173
Max Act: 8.3798. Min Act: -0.1700
Data Index: 956360 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8173. Min Range: -8.8173
Max Act: 8.4423. Min Act: -0.1700
Data Index: 8597587 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8173. Min Range: -8.8173
Max Act: 8.3798. Min Act: -0.1700
Data Index: 1607141 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8173. Min Range: -8.8173
Max Act: 8.3798. Min Act: -0.1700
Data Index: 8035484 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8173. Min Range: -8.8173
Max Act: 8.3173. Min Act: -0.1700
Data Index: 503444 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8173. Min Range: -8.8173
Max Act: 8.3173. Min Act: -0.1700
Data Index: 5926976 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8173. Min Range: -8.8173
Max Act: 8.3173. Min Act: -0.1700
Data Index: 8035485 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8173. Min Range: -8.8173
Max Act: 8.3173. Min Act: -0.1700
Data Index: 3204201 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8173. Min Range: -8.8173
Max Act: 8.2548. Min Act: -0.1700
Data Index: 2469963 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8173. Min Range: -8.8173
Max Act: 8.2548. Min Act: -0.1700
Data Index: 4887439 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8173. Min Range: -8.8173
Max Act: 8.2548. Min Act: -0.1700
Data Index: 2808680 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8173. Min Range: -8.8173
Max Act: 8.1298. Min Act: -0.1700
Data Index: 2109342 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8173. Min Range: -8.8173
Max Act: 8.1923. Min Act: -0.1700
Data Index: 2313563 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8173. Min Range: -8.8173
Max Act: 8.1298. Min Act: -0.1700
Data Index: 2086166 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8173. Min Range: -8.8173
Max Act: 8.1298. Min Act: -0.1700
Data Index: 3623772 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8173. Min Range: -8.8173
Max Act: 8.1298. Min Act: -0.1700
Data Index: 5411504 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19