Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5637 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1857. Min Range: -9.1857
Max Act: 9.1857. Min Act: -0.1700
Data Index: 396278 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1857. Min Range: -9.1857
Max Act: 9.1857. Min Act: -0.1700
Data Index: 2005615 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1857. Min Range: -9.1857
Max Act: 9.1232. Min Act: -0.1700
Data Index: 8571544 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1857. Min Range: -9.1857
Max Act: 9.1232. Min Act: -0.1700
Data Index: 7469833 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1857. Min Range: -9.1857
Max Act: 8.9982. Min Act: -0.1700
Data Index: 2600942 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1857. Min Range: -9.1857
Max Act: 8.8107. Min Act: -0.1700
Data Index: 7111018 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1857. Min Range: -9.1857
Max Act: 8.8107. Min Act: -0.1700
Data Index: 1897616 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1857. Min Range: -9.1857
Max Act: 8.7482. Min Act: -0.1700
Data Index: 5621580 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1857. Min Range: -9.1857
Max Act: 8.7482. Min Act: -0.1700
Data Index: 7484840 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1857. Min Range: -9.1857
Max Act: 8.7482. Min Act: -0.1700
Data Index: 6946131 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1857. Min Range: -9.1857
Max Act: 8.8107. Min Act: -0.1700
Data Index: 1636058 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1857. Min Range: -9.1857
Max Act: 8.6857. Min Act: -0.1700
Data Index: 3327921 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1857. Min Range: -9.1857
Max Act: 8.6857. Min Act: -0.1700
Data Index: 5444354 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1857. Min Range: -9.1857
Max Act: 8.6857. Min Act: -0.1700
Data Index: 693790 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1857. Min Range: -9.1857
Max Act: 8.6232. Min Act: -0.1700
Data Index: 3770760 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1857. Min Range: -9.1857
Max Act: 8.4982. Min Act: -0.1700
Data Index: 7155496 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1857. Min Range: -9.1857
Max Act: 8.5607. Min Act: -0.1700
Data Index: 8185037 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1857. Min Range: -9.1857
Max Act: 8.5607. Min Act: -0.1700
Data Index: 4622827 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1857. Min Range: -9.1857
Max Act: 8.4982. Min Act: -0.1700
Data Index: 642455 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1857. Min Range: -9.1857
Max Act: 8.4982. Min Act: -0.1700
Data Index: 4939997 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19