Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.9197. Min Act: -0.1700
Data Index: 4755024 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.7322. Min Act: -0.1700
Data Index: 4691887 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.6697. Min Act: -0.1700
Data Index: 5327618 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.6384. Min Act: -0.1700
Data Index: 4938434 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.6072. Min Act: -0.1700
Data Index: 406614 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.6072. Min Act: -0.1700
Data Index: 3212318 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.6072. Min Act: -0.1700
Data Index: 1340617 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.4822. Min Act: -0.1700
Data Index: 2834441 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.4822. Min Act: -0.1700
Data Index: 2044601 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.4822. Min Act: -0.1700
Data Index: 5751764 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.4509. Min Act: -0.1700
Data Index: 3030563 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.4197. Min Act: -0.1700
Data Index: 7637496 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.4197. Min Act: -0.1700
Data Index: 6947582 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.3884. Min Act: -0.1700
Data Index: 998906 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.4197. Min Act: -0.1700
Data Index: 5427791 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.3884. Min Act: -0.1700
Data Index: 4930291 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.3884. Min Act: -0.1700
Data Index: 1446951 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.3884. Min Act: -0.1700
Data Index: 3462720 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.3259. Min Act: -0.1700
Data Index: 2534875 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.3884. Min Act: -0.1700
Data Index: 1005833 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19