Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2634 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8705. Min Range: -5.8705
Max Act: 5.8705. Min Act: -0.1700
Data Index: 7087484 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8705. Min Range: -5.8705
Max Act: 5.5268. Min Act: -0.1700
Data Index: 5955851 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8705. Min Range: -5.8705
Max Act: 5.4643. Min Act: -0.1700
Data Index: 6097709 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8705. Min Range: -5.8705
Max Act: 5.3393. Min Act: -0.1700
Data Index: 5062260 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8705. Min Range: -5.8705
Max Act: 5.3080. Min Act: -0.1700
Data Index: 1353870 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8705. Min Range: -5.8705
Max Act: 5.2768. Min Act: -0.1700
Data Index: 5003018 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8705. Min Range: -5.8705
Max Act: 5.2143. Min Act: -0.1700
Data Index: 6677398 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8705. Min Range: -5.8705
Max Act: 5.1830. Min Act: -0.1700
Data Index: 935613 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8705. Min Range: -5.8705
Max Act: 5.1830. Min Act: -0.1700
Data Index: 5280042 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8705. Min Range: -5.8705
Max Act: 5.1830. Min Act: -0.1700
Data Index: 3674986 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8705. Min Range: -5.8705
Max Act: 5.1830. Min Act: -0.1700
Data Index: 1484957 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8705. Min Range: -5.8705
Max Act: 5.1205. Min Act: -0.1700
Data Index: 2313829 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8705. Min Range: -5.8705
Max Act: 5.1518. Min Act: -0.1700
Data Index: 5712737 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8705. Min Range: -5.8705
Max Act: 5.1205. Min Act: -0.1700
Data Index: 84287 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8705. Min Range: -5.8705
Max Act: 5.0893. Min Act: -0.1700
Data Index: 5192320 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8705. Min Range: -5.8705
Max Act: 5.0580. Min Act: -0.1700
Data Index: 338745 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8705. Min Range: -5.8705
Max Act: 5.0580. Min Act: -0.1700
Data Index: 7526991 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8705. Min Range: -5.8705
Max Act: 5.0580. Min Act: -0.1700
Data Index: 5027510 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8705. Min Range: -5.8705
Max Act: 5.0580. Min Act: -0.1700
Data Index: 6434898 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8705. Min Range: -5.8705
Max Act: 5.0268. Min Act: -0.1700
Data Index: 5823505 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19