Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4471 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.6898. Min Act: -0.1700
Data Index: 1701164 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.6585. Min Act: -0.1700
Data Index: 6336936 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.5960. Min Act: -0.1700
Data Index: 7480206 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.5960. Min Act: -0.1700
Data Index: 2427594 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.5335. Min Act: -0.1700
Data Index: 4117365 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.5023. Min Act: -0.1700
Data Index: 600213 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.5023. Min Act: -0.1700
Data Index: 1886720 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.5023. Min Act: -0.1700
Data Index: 2311892 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.4710. Min Act: -0.1699
Data Index: 2968433 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.4398. Min Act: -0.1700
Data Index: 2231362 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.4398. Min Act: -0.1700
Data Index: 4036411 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.4398. Min Act: -0.1700
Data Index: 4681467 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.4398. Min Act: -0.1700
Data Index: 5446272 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.4398. Min Act: -0.1700
Data Index: 7547683 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.4085. Min Act: -0.1700
Data Index: 200469 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.4085. Min Act: -0.1700
Data Index: 5046505 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.4085. Min Act: -0.1700
Data Index: 2039204 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.4085. Min Act: -0.1700
Data Index: 1862390 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.4398. Min Act: -0.1699
Data Index: 5950016 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.4085. Min Act: -0.1700
Data Index: 579994 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19