Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4221 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8717. Min Range: -7.8717
Max Act: 7.8717. Min Act: -0.1700
Data Index: 7603972 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8717. Min Range: -7.8717
Max Act: 7.8717. Min Act: -0.1700
Data Index: 4545194 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8717. Min Range: -7.8717
Max Act: 7.8717. Min Act: -0.1700
Data Index: 3725777 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8717. Min Range: -7.8717
Max Act: 7.8717. Min Act: -0.1700
Data Index: 3116637 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8717. Min Range: -7.8717
Max Act: 7.6217. Min Act: -0.1700
Data Index: 6238648 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8717. Min Range: -7.8717
Max Act: 7.5592. Min Act: -0.1700
Data Index: 1976930 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8717. Min Range: -7.8717
Max Act: 7.4967. Min Act: -0.1700
Data Index: 5025709 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8717. Min Range: -7.8717
Max Act: 7.4967. Min Act: -0.1700
Data Index: 3233920 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8717. Min Range: -7.8717
Max Act: 7.4967. Min Act: -0.1700
Data Index: 6098243 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8717. Min Range: -7.8717
Max Act: 7.4655. Min Act: -0.1700
Data Index: 4032316 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8717. Min Range: -7.8717
Max Act: 7.4655. Min Act: -0.1700
Data Index: 6772158 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8717. Min Range: -7.8717
Max Act: 7.4030. Min Act: -0.1700
Data Index: 4757266 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8717. Min Range: -7.8717
Max Act: 7.4342. Min Act: -0.1700
Data Index: 6413976 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8717. Min Range: -7.8717
Max Act: 7.4030. Min Act: -0.1700
Data Index: 6491420 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8717. Min Range: -7.8717
Max Act: 7.4342. Min Act: -0.1700
Data Index: 7033810 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8717. Min Range: -7.8717
Max Act: 7.4030. Min Act: -0.1700
Data Index: 126319 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8717. Min Range: -7.8717
Max Act: 7.4030. Min Act: -0.1700
Data Index: 6892725 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8717. Min Range: -7.8717
Max Act: 7.3717. Min Act: -0.1700
Data Index: 3817984 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8717. Min Range: -7.8717
Max Act: 7.3405. Min Act: -0.1700
Data Index: 6028648 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8717. Min Range: -7.8717
Max Act: 7.3405. Min Act: -0.1700
Data Index: 3234311 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19