Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3464 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9728. Min Range: -6.9728
Max Act: 6.9728. Min Act: -0.1700
Data Index: 5319691 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9728. Min Range: -6.9728
Max Act: 6.8478. Min Act: -0.1700
Data Index: 2249697 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9728. Min Range: -6.9728
Max Act: 6.6916. Min Act: -0.1700
Data Index: 4116742 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9728. Min Range: -6.9728
Max Act: 6.6291. Min Act: -0.1700
Data Index: 8027291 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9728. Min Range: -6.9728
Max Act: 6.5978. Min Act: -0.1700
Data Index: 4342541 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9728. Min Range: -6.9728
Max Act: 6.5978. Min Act: -0.1700
Data Index: 5213626 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9728. Min Range: -6.9728
Max Act: 6.5666. Min Act: -0.1700
Data Index: 4398864 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9728. Min Range: -6.9728
Max Act: 6.5666. Min Act: -0.1700
Data Index: 5716037 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9728. Min Range: -6.9728
Max Act: 6.5353. Min Act: -0.1700
Data Index: 2846053 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9728. Min Range: -6.9728
Max Act: 6.5041. Min Act: -0.1700
Data Index: 1966056 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9728. Min Range: -6.9728
Max Act: 6.4416. Min Act: -0.1700
Data Index: 925712 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9728. Min Range: -6.9728
Max Act: 6.4103. Min Act: -0.1700
Data Index: 3202842 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9728. Min Range: -6.9728
Max Act: 6.4416. Min Act: -0.1700
Data Index: 1156119 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9728. Min Range: -6.9728
Max Act: 6.4103. Min Act: -0.1700
Data Index: 8197600 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9728. Min Range: -6.9728
Max Act: 6.4103. Min Act: -0.1700
Data Index: 2072242 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9728. Min Range: -6.9728
Max Act: 6.4103. Min Act: -0.1700
Data Index: 4805243 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9728. Min Range: -6.9728
Max Act: 6.4103. Min Act: -0.1700
Data Index: 8271016 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9728. Min Range: -6.9728
Max Act: 6.4103. Min Act: -0.1700
Data Index: 7379868 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9728. Min Range: -6.9728
Max Act: 6.4103. Min Act: -0.1700
Data Index: 7882348 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9728. Min Range: -6.9728
Max Act: 6.3791. Min Act: -0.1700
Data Index: 2289547 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19