Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 307 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8363. Min Range: -3.8363
Max Act: 3.8363. Min Act: -0.1700
Data Index: 5717283 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8363. Min Range: -3.8363
Max Act: 3.8363. Min Act: -0.1700
Data Index: 5743027 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8363. Min Range: -3.8363
Max Act: 3.7268. Min Act: -0.1700
Data Index: 6712405 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8363. Min Range: -3.8363
Max Act: 3.7112. Min Act: -0.1700
Data Index: 6923944 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8363. Min Range: -3.8363
Max Act: 3.7112. Min Act: -0.1700
Data Index: 4892020 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8363. Min Range: -3.8363
Max Act: 3.6955. Min Act: -0.1700
Data Index: 4010718 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8363. Min Range: -3.8363
Max Act: 3.7112. Min Act: -0.1700
Data Index: 4972638 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8363. Min Range: -3.8363
Max Act: 3.6955. Min Act: -0.1700
Data Index: 4957088 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8363. Min Range: -3.8363
Max Act: 3.6642. Min Act: -0.1700
Data Index: 2302031 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8363. Min Range: -3.8363
Max Act: 3.6799. Min Act: -0.1700
Data Index: 3472424 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8363. Min Range: -3.8363
Max Act: 3.6642. Min Act: -0.1700
Data Index: 896624 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8363. Min Range: -3.8363
Max Act: 3.6486. Min Act: -0.1700
Data Index: 2120635 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8363. Min Range: -3.8363
Max Act: 3.6329. Min Act: -0.1700
Data Index: 3041341 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8363. Min Range: -3.8363
Max Act: 3.6486. Min Act: -0.1700
Data Index: 862867 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8363. Min Range: -3.8363
Max Act: 3.6329. Min Act: -0.1700
Data Index: 2669959 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8363. Min Range: -3.8363
Max Act: 3.6329. Min Act: -0.1700
Data Index: 2669957 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8363. Min Range: -3.8363
Max Act: 3.6329. Min Act: -0.1700
Data Index: 6515532 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8363. Min Range: -3.8363
Max Act: 3.6173. Min Act: -0.1700
Data Index: 2669963 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8363. Min Range: -3.8363
Max Act: 3.6486. Min Act: -0.1700
Data Index: 7105071 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8363. Min Range: -3.8363
Max Act: 3.6173. Min Act: -0.1700
Data Index: 6484931 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19