Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2003 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6097. Min Range: -6.6097
Max Act: 6.6097. Min Act: -0.1700
Data Index: 3384317 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6097. Min Range: -6.6097
Max Act: 6.3909. Min Act: -0.1700
Data Index: 3814116 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6097. Min Range: -6.6097
Max Act: 6.4222. Min Act: -0.1700
Data Index: 4879040 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6097. Min Range: -6.6097
Max Act: 6.3909. Min Act: -0.1700
Data Index: 5144032 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6097. Min Range: -6.6097
Max Act: 6.3284. Min Act: -0.1700
Data Index: 7225729 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6097. Min Range: -6.6097
Max Act: 6.3284. Min Act: -0.1700
Data Index: 8308319 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6097. Min Range: -6.6097
Max Act: 6.1722. Min Act: -0.1700
Data Index: 4041762 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6097. Min Range: -6.6097
Max Act: 6.1409. Min Act: -0.1700
Data Index: 4771790 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6097. Min Range: -6.6097
Max Act: 6.1409. Min Act: -0.1700
Data Index: 6089665 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6097. Min Range: -6.6097
Max Act: 6.1409. Min Act: -0.1700
Data Index: 7507645 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6097. Min Range: -6.6097
Max Act: 6.1097. Min Act: -0.1700
Data Index: 3380133 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6097. Min Range: -6.6097
Max Act: 6.1097. Min Act: -0.1700
Data Index: 6799115 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6097. Min Range: -6.6097
Max Act: 6.1097. Min Act: -0.1700
Data Index: 2339356 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6097. Min Range: -6.6097
Max Act: 6.0472. Min Act: -0.1700
Data Index: 6755443 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6097. Min Range: -6.6097
Max Act: 6.0159. Min Act: -0.1700
Data Index: 1467523 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6097. Min Range: -6.6097
Max Act: 5.9847. Min Act: -0.1700
Data Index: 1641339 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6097. Min Range: -6.6097
Max Act: 5.9222. Min Act: -0.1700
Data Index: 7774928 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6097. Min Range: -6.6097
Max Act: 5.8909. Min Act: -0.1700
Data Index: 6596620 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6097. Min Range: -6.6097
Max Act: 5.8909. Min Act: -0.1700
Data Index: 1922873 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6097. Min Range: -6.6097
Max Act: 5.8597. Min Act: -0.1700
Data Index: 4373683 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19