Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2348 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5315. Min Range: -6.5315
Max Act: 6.5315. Min Act: -0.1700
Data Index: 6158493 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5315. Min Range: -6.5315
Max Act: 6.5002. Min Act: -0.1700
Data Index: 8706908 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5315. Min Range: -6.5315
Max Act: 6.4690. Min Act: -0.1700
Data Index: 8372030 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5315. Min Range: -6.5315
Max Act: 6.4377. Min Act: -0.1700
Data Index: 1226845 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5315. Min Range: -6.5315
Max Act: 6.4690. Min Act: -0.1700
Data Index: 1973949 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5315. Min Range: -6.5315
Max Act: 6.3440. Min Act: -0.1700
Data Index: 3399070 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5315. Min Range: -6.5315
Max Act: 6.4065. Min Act: -0.1700
Data Index: 4010497 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5315. Min Range: -6.5315
Max Act: 6.2502. Min Act: -0.1700
Data Index: 7371111 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5315. Min Range: -6.5315
Max Act: 6.2502. Min Act: -0.1700
Data Index: 5505081 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5315. Min Range: -6.5315
Max Act: 6.2502. Min Act: -0.1700
Data Index: 7910082 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5315. Min Range: -6.5315
Max Act: 6.2502. Min Act: -0.1700
Data Index: 4097227 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5315. Min Range: -6.5315
Max Act: 6.2190. Min Act: -0.1700
Data Index: 40032 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5315. Min Range: -6.5315
Max Act: 6.1877. Min Act: -0.1700
Data Index: 1443387 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5315. Min Range: -6.5315
Max Act: 6.2190. Min Act: -0.1700
Data Index: 8357682 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5315. Min Range: -6.5315
Max Act: 6.1877. Min Act: -0.1700
Data Index: 8633160 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5315. Min Range: -6.5315
Max Act: 6.1565. Min Act: -0.1700
Data Index: 3806699 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5315. Min Range: -6.5315
Max Act: 6.1877. Min Act: -0.1700
Data Index: 4815872 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5315. Min Range: -6.5315
Max Act: 6.1252. Min Act: -0.1700
Data Index: 5912046 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5315. Min Range: -6.5315
Max Act: 6.1565. Min Act: -0.1700
Data Index: 8700346 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5315. Min Range: -6.5315
Max Act: 6.1565. Min Act: -0.1700
Data Index: 922807 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19