Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 819 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5511. Min Range: -6.5511
Max Act: 6.5511. Min Act: -0.1700
Data Index: 497954 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5511. Min Range: -6.5511
Max Act: 6.2074. Min Act: -0.1700
Data Index: 8457407 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5511. Min Range: -6.5511
Max Act: 6.1449. Min Act: -0.1700
Data Index: 2687407 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5511. Min Range: -6.5511
Max Act: 6.1449. Min Act: -0.1700
Data Index: 4794373 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5511. Min Range: -6.5511
Max Act: 6.0824. Min Act: -0.1700
Data Index: 4902300 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5511. Min Range: -6.5511
Max Act: 6.0824. Min Act: -0.1700
Data Index: 1350803 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5511. Min Range: -6.5511
Max Act: 6.0511. Min Act: -0.1700
Data Index: 6175646 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5511. Min Range: -6.5511
Max Act: 6.0199. Min Act: -0.1700
Data Index: 6078928 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5511. Min Range: -6.5511
Max Act: 6.0511. Min Act: -0.1700
Data Index: 6689071 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.9886. Min Act: -0.1700
Data Index: 1551548 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5511. Min Range: -6.5511
Max Act: 6.0199. Min Act: -0.1700
Data Index: 964118 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.9886. Min Act: -0.1700
Data Index: 6336732 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.9886. Min Act: -0.1700
Data Index: 4637466 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.9574. Min Act: -0.1700
Data Index: 8800214 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.9574. Min Act: -0.1700
Data Index: 2370923 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.9574. Min Act: -0.1700
Data Index: 2004546 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.9574. Min Act: -0.1700
Data Index: 8505339 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.9261. Min Act: -0.1700
Data Index: 1646284 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.9261. Min Act: -0.1700
Data Index: 6195522 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.9261. Min Act: -0.1700
Data Index: 7007547 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19