Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6064 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1100. Min Range: -8.1100
Max Act: 8.1100. Min Act: -0.1700
Data Index: 7116955 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1100. Min Range: -8.1100
Max Act: 7.6413. Min Act: -0.1700
Data Index: 168360 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1100. Min Range: -8.1100
Max Act: 7.5475. Min Act: -0.1700
Data Index: 6803532 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1100. Min Range: -8.1100
Max Act: 7.5163. Min Act: -0.1699
Data Index: 6167614 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1100. Min Range: -8.1100
Max Act: 7.4850. Min Act: -0.1700
Data Index: 968575 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1100. Min Range: -8.1100
Max Act: 7.4538. Min Act: -0.1700
Data Index: 6803537 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1100. Min Range: -8.1100
Max Act: 7.4538. Min Act: -0.1700
Data Index: 4986908 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1100. Min Range: -8.1100
Max Act: 7.4225. Min Act: -0.1700
Data Index: 123502 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1100. Min Range: -8.1100
Max Act: 7.3288. Min Act: -0.1700
Data Index: 4124148 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1100. Min Range: -8.1100
Max Act: 7.3600. Min Act: -0.1700
Data Index: 1534516 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1100. Min Range: -8.1100
Max Act: 7.3288. Min Act: -0.1700
Data Index: 5302385 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1100. Min Range: -8.1100
Max Act: 7.2975. Min Act: -0.1700
Data Index: 5100571 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1100. Min Range: -8.1100
Max Act: 7.2663. Min Act: -0.1700
Data Index: 6539559 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1100. Min Range: -8.1100
Max Act: 7.2350. Min Act: -0.1700
Data Index: 4591797 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1100. Min Range: -8.1100
Max Act: 7.2038. Min Act: -0.1700
Data Index: 5183127 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1100. Min Range: -8.1100
Max Act: 7.2038. Min Act: -0.1700
Data Index: 2982522 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1100. Min Range: -8.1100
Max Act: 7.2038. Min Act: -0.1700
Data Index: 7306982 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1100. Min Range: -8.1100
Max Act: 7.1413. Min Act: -0.1700
Data Index: 5501782 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1100. Min Range: -8.1100
Max Act: 7.1725. Min Act: -0.1700
Data Index: 1977188 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1100. Min Range: -8.1100
Max Act: 7.1413. Min Act: -0.1700
Data Index: 168359 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19