Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2591 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4922. Min Range: -3.4922
Max Act: 3.4922. Min Act: -0.1700
Data Index: 3650774 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4922. Min Range: -3.4922
Max Act: 3.4922. Min Act: -0.1700
Data Index: 1902466 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4922. Min Range: -3.4922
Max Act: 3.4609. Min Act: -0.1700
Data Index: 6750632 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4922. Min Range: -3.4922
Max Act: 3.4765. Min Act: -0.1700
Data Index: 2277090 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4922. Min Range: -3.4922
Max Act: 3.4765. Min Act: -0.1700
Data Index: 8072916 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4922. Min Range: -3.4922
Max Act: 3.4452. Min Act: -0.1700
Data Index: 3398641 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4922. Min Range: -3.4922
Max Act: 3.4452. Min Act: -0.1700
Data Index: 6653635 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4922. Min Range: -3.4922
Max Act: 3.3982. Min Act: -0.1700
Data Index: 4084127 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4922. Min Range: -3.4922
Max Act: 3.3668. Min Act: -0.1700
Data Index: 543719 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4922. Min Range: -3.4922
Max Act: 3.3668. Min Act: -0.1700
Data Index: 435116 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4922. Min Range: -3.4922
Max Act: 3.3668. Min Act: -0.1700
Data Index: 1820299 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4922. Min Range: -3.4922
Max Act: 3.3511. Min Act: -0.1700
Data Index: 4530308 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4922. Min Range: -3.4922
Max Act: 3.3825. Min Act: -0.1700
Data Index: 2667100 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4922. Min Range: -3.4922
Max Act: 3.3355. Min Act: -0.1700
Data Index: 2071581 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4922. Min Range: -3.4922
Max Act: 3.2884. Min Act: -0.1700
Data Index: 1884562 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4922. Min Range: -3.4922
Max Act: 3.3198. Min Act: -0.1700
Data Index: 6084499 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4922. Min Range: -3.4922
Max Act: 3.3198. Min Act: -0.1700
Data Index: 932525 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4922. Min Range: -3.4922
Max Act: 3.3355. Min Act: -0.1700
Data Index: 130239 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4922. Min Range: -3.4922
Max Act: 3.3355. Min Act: -0.1700
Data Index: 7128426 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4922. Min Range: -3.4922
Max Act: 3.3198. Min Act: -0.1700
Data Index: 7760740 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19