Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 575 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4303. Min Range: -11.4303
Max Act: 11.4303. Min Act: -0.1700
Data Index: 6792047 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4303. Min Range: -11.4303
Max Act: 11.3678. Min Act: -0.1700
Data Index: 5244124 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4303. Min Range: -11.4303
Max Act: 11.3678. Min Act: -0.1700
Data Index: 4495024 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4303. Min Range: -11.4303
Max Act: 11.3678. Min Act: -0.1700
Data Index: 4938228 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4303. Min Range: -11.4303
Max Act: 11.2428. Min Act: -0.1700
Data Index: 1213536 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4303. Min Range: -11.4303
Max Act: 11.3053. Min Act: -0.1700
Data Index: 4268603 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4303. Min Range: -11.4303
Max Act: 11.1803. Min Act: -0.1700
Data Index: 3793623 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4303. Min Range: -11.4303
Max Act: 11.1178. Min Act: -0.1700
Data Index: 1726564 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4303. Min Range: -11.4303
Max Act: 11.1178. Min Act: -0.1700
Data Index: 5478749 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4303. Min Range: -11.4303
Max Act: 11.0553. Min Act: -0.1700
Data Index: 8300859 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4303. Min Range: -11.4303
Max Act: 11.0553. Min Act: -0.1700
Data Index: 6468649 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4303. Min Range: -11.4303
Max Act: 11.0553. Min Act: -0.1700
Data Index: 359307 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4303. Min Range: -11.4303
Max Act: 11.0553. Min Act: -0.1700
Data Index: 3251605 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4303. Min Range: -11.4303
Max Act: 10.9928. Min Act: -0.1700
Data Index: 3793602 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4303. Min Range: -11.4303
Max Act: 10.9928. Min Act: -0.1700
Data Index: 4939706 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4303. Min Range: -11.4303
Max Act: 10.9928. Min Act: -0.1700
Data Index: 806988 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4303. Min Range: -11.4303
Max Act: 10.9303. Min Act: -0.1700
Data Index: 4652977 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4303. Min Range: -11.4303
Max Act: 10.9303. Min Act: -0.1700
Data Index: 3793612 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4303. Min Range: -11.4303
Max Act: 10.9303. Min Act: -0.1700
Data Index: 5121633 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4303. Min Range: -11.4303
Max Act: 10.8678. Min Act: -0.1700
Data Index: 2320 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19