Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4864 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9353. Min Range: -7.9353
Max Act: 7.9353. Min Act: -0.1700
Data Index: 4339763 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9353. Min Range: -7.9353
Max Act: 7.8728. Min Act: -0.1700
Data Index: 5110660 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9353. Min Range: -7.9353
Max Act: 7.8103. Min Act: -0.1700
Data Index: 430688 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9353. Min Range: -7.9353
Max Act: 7.8103. Min Act: -0.1700
Data Index: 4468826 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9353. Min Range: -7.9353
Max Act: 7.8103. Min Act: -0.1700
Data Index: 4327952 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9353. Min Range: -7.9353
Max Act: 7.7478. Min Act: -0.1700
Data Index: 1560163 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9353. Min Range: -7.9353
Max Act: 7.7478. Min Act: -0.1700
Data Index: 4641585 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9353. Min Range: -7.9353
Max Act: 7.6853. Min Act: -0.1700
Data Index: 747684 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9353. Min Range: -7.9353
Max Act: 7.6228. Min Act: -0.1700
Data Index: 1674127 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9353. Min Range: -7.9353
Max Act: 7.6228. Min Act: -0.1700
Data Index: 1045167 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9353. Min Range: -7.9353
Max Act: 7.5916. Min Act: -0.1700
Data Index: 7617414 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9353. Min Range: -7.9353
Max Act: 7.5916. Min Act: -0.1700
Data Index: 5623803 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9353. Min Range: -7.9353
Max Act: 7.5603. Min Act: -0.1700
Data Index: 1375734 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9353. Min Range: -7.9353
Max Act: 7.4978. Min Act: -0.1700
Data Index: 1329479 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9353. Min Range: -7.9353
Max Act: 7.4978. Min Act: -0.1700
Data Index: 7603643 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9353. Min Range: -7.9353
Max Act: 7.4353. Min Act: -0.1700
Data Index: 1022127 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9353. Min Range: -7.9353
Max Act: 7.4353. Min Act: -0.1700
Data Index: 7742971 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9353. Min Range: -7.9353
Max Act: 7.4353. Min Act: -0.1700
Data Index: 4989332 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9353. Min Range: -7.9353
Max Act: 7.4666. Min Act: -0.1700
Data Index: 2567149 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9353. Min Range: -7.9353
Max Act: 7.4041. Min Act: -0.1700
Data Index: 5688374 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19