Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 535 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6941. Min Range: -5.6941
Max Act: 5.6941. Min Act: -0.1700
Data Index: 1467834 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6941. Min Range: -5.6941
Max Act: 5.2253. Min Act: -0.1700
Data Index: 3832223 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6941. Min Range: -5.6941
Max Act: 5.1628. Min Act: -0.1700
Data Index: 3380252 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6941. Min Range: -5.6941
Max Act: 5.1316. Min Act: -0.1700
Data Index: 4649045 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6941. Min Range: -5.6941
Max Act: 5.0691. Min Act: -0.1700
Data Index: 3828696 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6941. Min Range: -5.6941
Max Act: 5.0691. Min Act: -0.1700
Data Index: 3802795 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6941. Min Range: -5.6941
Max Act: 5.0691. Min Act: -0.1700
Data Index: 5046464 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6941. Min Range: -5.6941
Max Act: 5.0378. Min Act: -0.1700
Data Index: 5559689 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6941. Min Range: -5.6941
Max Act: 5.0378. Min Act: -0.1700
Data Index: 112562 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6941. Min Range: -5.6941
Max Act: 5.0378. Min Act: -0.1700
Data Index: 6343260 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6941. Min Range: -5.6941
Max Act: 5.0378. Min Act: -0.1700
Data Index: 4106227 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6941. Min Range: -5.6941
Max Act: 5.0066. Min Act: -0.1700
Data Index: 1659643 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6941. Min Range: -5.6941
Max Act: 5.0066. Min Act: -0.1700
Data Index: 1892578 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6941. Min Range: -5.6941
Max Act: 4.9441. Min Act: -0.1700
Data Index: 2499238 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6941. Min Range: -5.6941
Max Act: 4.9441. Min Act: -0.1700
Data Index: 538808 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6941. Min Range: -5.6941
Max Act: 4.9441. Min Act: -0.1700
Data Index: 8123450 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6941. Min Range: -5.6941
Max Act: 4.9128. Min Act: -0.1700
Data Index: 3966567 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6941. Min Range: -5.6941
Max Act: 4.9441. Min Act: -0.1700
Data Index: 3434959 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6941. Min Range: -5.6941
Max Act: 4.8816. Min Act: -0.1700
Data Index: 1515004 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6941. Min Range: -5.6941
Max Act: 4.8816. Min Act: -0.1700
Data Index: 6405976 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19