Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3500 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0813. Min Range: -11.0813
Max Act: 11.0813. Min Act: -0.1700
Data Index: 6143090 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0813. Min Range: -11.0813
Max Act: 10.8938. Min Act: -0.1700
Data Index: 3490666 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0813. Min Range: -11.0813
Max Act: 10.5813. Min Act: -0.1700
Data Index: 3490670 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0813. Min Range: -11.0813
Max Act: 10.5813. Min Act: -0.1700
Data Index: 2913877 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0813. Min Range: -11.0813
Max Act: 10.5188. Min Act: -0.1700
Data Index: 7163901 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0813. Min Range: -11.0813
Max Act: 10.5188. Min Act: -0.1700
Data Index: 5405686 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0813. Min Range: -11.0813
Max Act: 10.3938. Min Act: -0.1700
Data Index: 8640002 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0813. Min Range: -11.0813
Max Act: 10.3938. Min Act: -0.1700
Data Index: 2655349 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0813. Min Range: -11.0813
Max Act: 10.4563. Min Act: -0.1700
Data Index: 4136621 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0813. Min Range: -11.0813
Max Act: 10.3938. Min Act: -0.1700
Data Index: 7759322 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0813. Min Range: -11.0813
Max Act: 10.3938. Min Act: -0.1700
Data Index: 243295 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0813. Min Range: -11.0813
Max Act: 10.3938. Min Act: -0.1700
Data Index: 8291740 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0813. Min Range: -11.0813
Max Act: 10.3313. Min Act: -0.1700
Data Index: 6143089 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0813. Min Range: -11.0813
Max Act: 10.3313. Min Act: -0.1700
Data Index: 8795461 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0813. Min Range: -11.0813
Max Act: 10.2688. Min Act: -0.1700
Data Index: 3490673 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0813. Min Range: -11.0813
Max Act: 10.2688. Min Act: -0.1700
Data Index: 3490681 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0813. Min Range: -11.0813
Max Act: 10.2688. Min Act: -0.1700
Data Index: 2655320 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0813. Min Range: -11.0813
Max Act: 10.2063. Min Act: -0.1700
Data Index: 8096644 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0813. Min Range: -11.0813
Max Act: 10.1438. Min Act: -0.1700
Data Index: 7627420 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0813. Min Range: -11.0813
Max Act: 10.1438. Min Act: -0.1700
Data Index: 7387231 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19