Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5523. Min Range: -5.5523
Max Act: 5.5523. Min Act: -0.1700
Data Index: 3168801 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5523. Min Range: -5.5523
Max Act: 5.5210. Min Act: -0.1700
Data Index: 3031012 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5523. Min Range: -5.5523
Max Act: 5.4273. Min Act: -0.1700
Data Index: 97978 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5523. Min Range: -5.5523
Max Act: 5.3960. Min Act: -0.1700
Data Index: 8108555 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5523. Min Range: -5.5523
Max Act: 5.3648. Min Act: -0.1700
Data Index: 3821496 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5523. Min Range: -5.5523
Max Act: 5.3648. Min Act: -0.1700
Data Index: 5217414 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5523. Min Range: -5.5523
Max Act: 5.3648. Min Act: -0.1700
Data Index: 7066469 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5523. Min Range: -5.5523
Max Act: 5.3023. Min Act: -0.1700
Data Index: 4840764 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5523. Min Range: -5.5523
Max Act: 5.3023. Min Act: -0.1700
Data Index: 2911061 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5523. Min Range: -5.5523
Max Act: 5.3335. Min Act: -0.1700
Data Index: 5948682 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5523. Min Range: -5.5523
Max Act: 5.3023. Min Act: -0.1700
Data Index: 6736496 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5523. Min Range: -5.5523
Max Act: 5.3023. Min Act: -0.1700
Data Index: 195872 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5523. Min Range: -5.5523
Max Act: 5.2710. Min Act: -0.1700
Data Index: 6992868 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5523. Min Range: -5.5523
Max Act: 5.2710. Min Act: -0.1700
Data Index: 5695560 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5523. Min Range: -5.5523
Max Act: 5.2398. Min Act: -0.1700
Data Index: 732223 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5523. Min Range: -5.5523
Max Act: 5.2398. Min Act: -0.1700
Data Index: 937310 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5523. Min Range: -5.5523
Max Act: 5.2710. Min Act: -0.1700
Data Index: 5750225 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5523. Min Range: -5.5523
Max Act: 5.2398. Min Act: -0.1700
Data Index: 7270699 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5523. Min Range: -5.5523
Max Act: 5.2398. Min Act: -0.1700
Data Index: 5910619 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5523. Min Range: -5.5523
Max Act: 5.2398. Min Act: -0.1700
Data Index: 2359738 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19