Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2327 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1508. Min Range: -4.1508
Max Act: 4.1508. Min Act: -0.1700
Data Index: 3939546 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1508. Min Range: -4.1508
Max Act: 4.0883. Min Act: -0.1700
Data Index: 512716 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1508. Min Range: -4.1508
Max Act: 4.0102. Min Act: -0.1700
Data Index: 1958713 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1508. Min Range: -4.1508
Max Act: 3.9633. Min Act: -0.1700
Data Index: 7096735 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1508. Min Range: -4.1508
Max Act: 3.9320. Min Act: -0.1700
Data Index: 302616 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1508. Min Range: -4.1508
Max Act: 3.9164. Min Act: -0.1700
Data Index: 3642699 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1508. Min Range: -4.1508
Max Act: 3.9320. Min Act: -0.1700
Data Index: 5201738 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1508. Min Range: -4.1508
Max Act: 3.9164. Min Act: -0.1700
Data Index: 1777465 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1508. Min Range: -4.1508
Max Act: 3.8851. Min Act: -0.1700
Data Index: 7832994 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1508. Min Range: -4.1508
Max Act: 3.9164. Min Act: -0.1700
Data Index: 2893541 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1508. Min Range: -4.1508
Max Act: 3.8851. Min Act: -0.1700
Data Index: 5657753 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1508. Min Range: -4.1508
Max Act: 3.8695. Min Act: -0.1700
Data Index: 2735748 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1508. Min Range: -4.1508
Max Act: 3.8382. Min Act: -0.1700
Data Index: 4165898 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1508. Min Range: -4.1508
Max Act: 3.8226. Min Act: -0.1700
Data Index: 5518450 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1508. Min Range: -4.1508
Max Act: 3.8226. Min Act: -0.1700
Data Index: 1005580 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1508. Min Range: -4.1508
Max Act: 3.8226. Min Act: -0.1700
Data Index: 7497860 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1508. Min Range: -4.1508
Max Act: 3.8070. Min Act: -0.1700
Data Index: 3232328 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1508. Min Range: -4.1508
Max Act: 3.8070. Min Act: -0.1700
Data Index: 6916817 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1508. Min Range: -4.1508
Max Act: 3.7600. Min Act: -0.1700
Data Index: 4067787 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1508. Min Range: -4.1508
Max Act: 3.7757. Min Act: -0.1700
Data Index: 2079674 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19