Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5217 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6104. Min Range: -7.6104
Max Act: 7.6104. Min Act: -0.1700
Data Index: 6449238 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6104. Min Range: -7.6104
Max Act: 7.4541. Min Act: -0.1700
Data Index: 6128754 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6104. Min Range: -7.6104
Max Act: 7.3291. Min Act: -0.1700
Data Index: 6097104 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6104. Min Range: -7.6104
Max Act: 7.3604. Min Act: -0.1700
Data Index: 4236059 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6104. Min Range: -7.6104
Max Act: 7.1729. Min Act: -0.1700
Data Index: 7506033 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6104. Min Range: -7.6104
Max Act: 7.1416. Min Act: -0.1700
Data Index: 8252506 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6104. Min Range: -7.6104
Max Act: 7.1104. Min Act: -0.1700
Data Index: 942576 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6104. Min Range: -7.6104
Max Act: 7.0791. Min Act: -0.1700
Data Index: 6097077 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6104. Min Range: -7.6104
Max Act: 6.9854. Min Act: -0.1700
Data Index: 5001181 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6104. Min Range: -7.6104
Max Act: 6.9854. Min Act: -0.1700
Data Index: 6097098 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6104. Min Range: -7.6104
Max Act: 6.9854. Min Act: -0.1700
Data Index: 6097078 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6104. Min Range: -7.6104
Max Act: 6.9229. Min Act: -0.1700
Data Index: 6128753 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6104. Min Range: -7.6104
Max Act: 6.8916. Min Act: -0.1700
Data Index: 4553257 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6104. Min Range: -7.6104
Max Act: 6.8291. Min Act: -0.1700
Data Index: 3554834 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6104. Min Range: -7.6104
Max Act: 6.8291. Min Act: -0.1700
Data Index: 6449241 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6104. Min Range: -7.6104
Max Act: 6.7979. Min Act: -0.1700
Data Index: 610982 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6104. Min Range: -7.6104
Max Act: 6.7666. Min Act: -0.1700
Data Index: 8119587 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6104. Min Range: -7.6104
Max Act: 6.7666. Min Act: -0.1700
Data Index: 6097083 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6104. Min Range: -7.6104
Max Act: 6.7041. Min Act: -0.1700
Data Index: 5349014 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6104. Min Range: -7.6104
Max Act: 6.7041. Min Act: -0.1700
Data Index: 6870902 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19