Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3091 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.4598. Min Range: -12.4598
Max Act: 12.4598. Min Act: -0.1700
Data Index: 3482320 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4598. Min Range: -12.4598
Max Act: 12.3348. Min Act: -0.1700
Data Index: 117357 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4598. Min Range: -12.4598
Max Act: 12.0848. Min Act: -0.1700
Data Index: 4488503 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4598. Min Range: -12.4598
Max Act: 12.0223. Min Act: -0.1700
Data Index: 2722748 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4598. Min Range: -12.4598
Max Act: 12.0223. Min Act: -0.1700
Data Index: 9845 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4598. Min Range: -12.4598
Max Act: 11.9598. Min Act: -0.1700
Data Index: 3587066 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4598. Min Range: -12.4598
Max Act: 11.9598. Min Act: -0.1700
Data Index: 6800792 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4598. Min Range: -12.4598
Max Act: 11.8973. Min Act: -0.1700
Data Index: 3424984 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4598. Min Range: -12.4598
Max Act: 11.8973. Min Act: -0.1700
Data Index: 6664571 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4598. Min Range: -12.4598
Max Act: 11.8973. Min Act: -0.1700
Data Index: 1450344 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4598. Min Range: -12.4598
Max Act: 11.8973. Min Act: -0.1700
Data Index: 80868 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4598. Min Range: -12.4598
Max Act: 11.8348. Min Act: -0.1700
Data Index: 2281285 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4598. Min Range: -12.4598
Max Act: 11.8348. Min Act: -0.1700
Data Index: 4727285 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4598. Min Range: -12.4598
Max Act: 11.8348. Min Act: -0.1700
Data Index: 6631920 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4598. Min Range: -12.4598
Max Act: 11.8348. Min Act: -0.1700
Data Index: 2099854 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4598. Min Range: -12.4598
Max Act: 11.7723. Min Act: -0.1700
Data Index: 690173 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4598. Min Range: -12.4598
Max Act: 11.7723. Min Act: -0.1700
Data Index: 3234886 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4598. Min Range: -12.4598
Max Act: 11.7723. Min Act: -0.1700
Data Index: 7110625 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4598. Min Range: -12.4598
Max Act: 11.7723. Min Act: -0.1700
Data Index: 662782 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4598. Min Range: -12.4598
Max Act: 11.7723. Min Act: -0.1700
Data Index: 1208405 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19