Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3867 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3402. Min Range: -6.3402
Max Act: 6.3402. Min Act: -0.1700
Data Index: 2906249 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3402. Min Range: -6.3402
Max Act: 6.2152. Min Act: -0.1700
Data Index: 4747422 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3402. Min Range: -6.3402
Max Act: 6.1214. Min Act: -0.1700
Data Index: 8644951 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3402. Min Range: -6.3402
Max Act: 6.0589. Min Act: -0.1700
Data Index: 3884937 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3402. Min Range: -6.3402
Max Act: 6.1214. Min Act: -0.1700
Data Index: 6126462 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3402. Min Range: -6.3402
Max Act: 6.0589. Min Act: -0.1700
Data Index: 4833309 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3402. Min Range: -6.3402
Max Act: 6.0589. Min Act: -0.1700
Data Index: 281391 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3402. Min Range: -6.3402
Max Act: 5.9964. Min Act: -0.1700
Data Index: 2043939 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3402. Min Range: -6.3402
Max Act: 5.9964. Min Act: -0.1700
Data Index: 503568 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3402. Min Range: -6.3402
Max Act: 5.9964. Min Act: -0.1700
Data Index: 5929925 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3402. Min Range: -6.3402
Max Act: 5.9964. Min Act: -0.1700
Data Index: 5670324 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3402. Min Range: -6.3402
Max Act: 5.9964. Min Act: -0.1700
Data Index: 6267406 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3402. Min Range: -6.3402
Max Act: 5.9652. Min Act: -0.1700
Data Index: 3607369 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3402. Min Range: -6.3402
Max Act: 5.9964. Min Act: -0.1700
Data Index: 3270090 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3402. Min Range: -6.3402
Max Act: 5.9964. Min Act: -0.1700
Data Index: 5471752 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3402. Min Range: -6.3402
Max Act: 5.9339. Min Act: -0.1700
Data Index: 2631733 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3402. Min Range: -6.3402
Max Act: 5.9652. Min Act: -0.1700
Data Index: 3931061 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3402. Min Range: -6.3402
Max Act: 5.9339. Min Act: -0.1700
Data Index: 6641021 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3402. Min Range: -6.3402
Max Act: 5.9027. Min Act: -0.1700
Data Index: 5259760 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3402. Min Range: -6.3402
Max Act: 5.9027. Min Act: -0.1700
Data Index: 7260710 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19