Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1654 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3291. Min Range: -9.3291
Max Act: 9.3291. Min Act: -0.1700
Data Index: 7849588 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3291. Min Range: -9.3291
Max Act: 9.2666. Min Act: -0.1700
Data Index: 1182607 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3291. Min Range: -9.3291
Max Act: 9.2041. Min Act: -0.1700
Data Index: 1152785 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3291. Min Range: -9.3291
Max Act: 9.1416. Min Act: -0.1700
Data Index: 5530642 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3291. Min Range: -9.3291
Max Act: 9.1416. Min Act: -0.1700
Data Index: 8682511 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3291. Min Range: -9.3291
Max Act: 9.1416. Min Act: -0.1700
Data Index: 1000659 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3291. Min Range: -9.3291
Max Act: 9.0791. Min Act: -0.1700
Data Index: 6855044 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3291. Min Range: -9.3291
Max Act: 9.0791. Min Act: -0.1700
Data Index: 6127569 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3291. Min Range: -9.3291
Max Act: 9.0166. Min Act: -0.1700
Data Index: 4517482 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3291. Min Range: -9.3291
Max Act: 9.0166. Min Act: -0.1700
Data Index: 1780094 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3291. Min Range: -9.3291
Max Act: 9.0166. Min Act: -0.1700
Data Index: 4199162 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3291. Min Range: -9.3291
Max Act: 8.8916. Min Act: -0.1700
Data Index: 2768907 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3291. Min Range: -9.3291
Max Act: 8.9541. Min Act: -0.1700
Data Index: 7432245 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3291. Min Range: -9.3291
Max Act: 8.8916. Min Act: -0.1700
Data Index: 5270263 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3291. Min Range: -9.3291
Max Act: 8.8916. Min Act: -0.1700
Data Index: 1117840 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3291. Min Range: -9.3291
Max Act: 8.8291. Min Act: -0.1700
Data Index: 376823 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3291. Min Range: -9.3291
Max Act: 8.8291. Min Act: -0.1700
Data Index: 7911839 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3291. Min Range: -9.3291
Max Act: 8.8291. Min Act: -0.1700
Data Index: 4933349 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3291. Min Range: -9.3291
Max Act: 8.7666. Min Act: -0.1700
Data Index: 4863175 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3291. Min Range: -9.3291
Max Act: 8.7041. Min Act: -0.1700
Data Index: 2158001 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19