Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3032 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.9208. Min Act: -0.1700
Data Index: 2896890 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.5770. Min Act: -0.1700
Data Index: 2679452 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.5145. Min Act: -0.1700
Data Index: 5343367 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.4833. Min Act: -0.1700
Data Index: 3100831 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.4520. Min Act: -0.1700
Data Index: 6262720 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.4208. Min Act: -0.1700
Data Index: 1260737 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.3895. Min Act: -0.1700
Data Index: 2324106 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.3583. Min Act: -0.1700
Data Index: 6845655 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.3583. Min Act: -0.1700
Data Index: 2172103 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.3270. Min Act: -0.1700
Data Index: 769800 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.3270. Min Act: -0.1700
Data Index: 1589590 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.3270. Min Act: -0.1700
Data Index: 3890825 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.2958. Min Act: -0.1700
Data Index: 7922761 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.2645. Min Act: -0.1700
Data Index: 4763765 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.2645. Min Act: -0.1700
Data Index: 3476470 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.2645. Min Act: -0.1700
Data Index: 2324994 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.2645. Min Act: -0.1700
Data Index: 3681418 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.2645. Min Act: -0.1700
Data Index: 6876907 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.2333. Min Act: -0.1700
Data Index: 6949451 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.2020. Min Act: -0.1700
Data Index: 2829236 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19