Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3544 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9416. Min Range: -7.9416
Max Act: 7.9416. Min Act: -0.1700
Data Index: 2479353 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9416. Min Range: -7.9416
Max Act: 7.8791. Min Act: -0.1700
Data Index: 4604992 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9416. Min Range: -7.9416
Max Act: 7.8791. Min Act: -0.1700
Data Index: 8283524 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9416. Min Range: -7.9416
Max Act: 7.8791. Min Act: -0.1700
Data Index: 5990220 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9416. Min Range: -7.9416
Max Act: 7.8166. Min Act: -0.1700
Data Index: 1902547 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9416. Min Range: -7.9416
Max Act: 7.7541. Min Act: -0.1700
Data Index: 1687422 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9416. Min Range: -7.9416
Max Act: 7.6916. Min Act: -0.1700
Data Index: 3065331 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9416. Min Range: -7.9416
Max Act: 7.6916. Min Act: -0.1700
Data Index: 4909434 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9416. Min Range: -7.9416
Max Act: 7.6916. Min Act: -0.1700
Data Index: 6080085 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9416. Min Range: -7.9416
Max Act: 7.6291. Min Act: -0.1700
Data Index: 4423912 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9416. Min Range: -7.9416
Max Act: 7.5666. Min Act: -0.1700
Data Index: 2245192 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9416. Min Range: -7.9416
Max Act: 7.6291. Min Act: -0.1700
Data Index: 2207419 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9416. Min Range: -7.9416
Max Act: 7.5666. Min Act: -0.1700
Data Index: 3498453 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9416. Min Range: -7.9416
Max Act: 7.5666. Min Act: -0.1700
Data Index: 1534211 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9416. Min Range: -7.9416
Max Act: 7.5666. Min Act: -0.1700
Data Index: 3491456 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9416. Min Range: -7.9416
Max Act: 7.5041. Min Act: -0.1700
Data Index: 3641619 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9416. Min Range: -7.9416
Max Act: 7.5041. Min Act: -0.1700
Data Index: 6005346 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9416. Min Range: -7.9416
Max Act: 7.5041. Min Act: -0.1700
Data Index: 6388821 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9416. Min Range: -7.9416
Max Act: 7.5041. Min Act: -0.1700
Data Index: 1806104 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9416. Min Range: -7.9416
Max Act: 7.4728. Min Act: -0.1700
Data Index: 5008617 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19