Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3722 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5338. Min Range: -3.5338
Max Act: 3.5338. Min Act: -0.1700
Data Index: 7078778 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5338. Min Range: -3.5338
Max Act: 3.4242. Min Act: -0.1700
Data Index: 8538625 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5338. Min Range: -3.5338
Max Act: 3.2673. Min Act: -0.1700
Data Index: 633953 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5338. Min Range: -3.5338
Max Act: 3.2359. Min Act: -0.1700
Data Index: 8606687 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5338. Min Range: -3.5338
Max Act: 3.2359. Min Act: -0.1700
Data Index: 3353529 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5338. Min Range: -3.5338
Max Act: 3.2201. Min Act: -0.1700
Data Index: 7000872 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5338. Min Range: -3.5338
Max Act: 3.2201. Min Act: -0.1700
Data Index: 5842410 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5338. Min Range: -3.5338
Max Act: 3.1887. Min Act: -0.1700
Data Index: 8113962 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5338. Min Range: -3.5338
Max Act: 3.1887. Min Act: -0.1700
Data Index: 1337818 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5338. Min Range: -3.5338
Max Act: 3.1730. Min Act: -0.1700
Data Index: 537462 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5338. Min Range: -3.5338
Max Act: 3.1887. Min Act: -0.1700
Data Index: 5885766 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5338. Min Range: -3.5338
Max Act: 3.1730. Min Act: -0.1700
Data Index: 4285379 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5338. Min Range: -3.5338
Max Act: 3.1730. Min Act: -0.1700
Data Index: 5544157 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5338. Min Range: -3.5338
Max Act: 3.1572. Min Act: -0.1700
Data Index: 6252435 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5338. Min Range: -3.5338
Max Act: 3.1572. Min Act: -0.1700
Data Index: 3056860 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5338. Min Range: -3.5338
Max Act: 3.1572. Min Act: -0.1700
Data Index: 4249733 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5338. Min Range: -3.5338
Max Act: 3.1572. Min Act: -0.1700
Data Index: 1034212 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5338. Min Range: -3.5338
Max Act: 3.1257. Min Act: -0.1700
Data Index: 733359 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5338. Min Range: -3.5338
Max Act: 3.1257. Min Act: -0.1700
Data Index: 7576087 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5338. Min Range: -3.5338
Max Act: 3.1100. Min Act: -0.1700
Data Index: 4060169 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19