Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4008. Min Range: -6.4008
Max Act: 6.4008. Min Act: -0.1700
Data Index: 4107488 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4008. Min Range: -6.4008
Max Act: 6.2445. Min Act: -0.1700
Data Index: 390251 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4008. Min Range: -6.4008
Max Act: 6.2133. Min Act: -0.1700
Data Index: 449911 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4008. Min Range: -6.4008
Max Act: 6.2133. Min Act: -0.1700
Data Index: 1217903 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4008. Min Range: -6.4008
Max Act: 6.1508. Min Act: -0.1700
Data Index: 3460376 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4008. Min Range: -6.4008
Max Act: 6.1195. Min Act: -0.1700
Data Index: 5927214 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4008. Min Range: -6.4008
Max Act: 6.0883. Min Act: -0.1700
Data Index: 8251024 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4008. Min Range: -6.4008
Max Act: 6.0570. Min Act: -0.1700
Data Index: 435938 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4008. Min Range: -6.4008
Max Act: 6.0570. Min Act: -0.1700
Data Index: 7390366 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4008. Min Range: -6.4008
Max Act: 6.0258. Min Act: -0.1700
Data Index: 186510 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4008. Min Range: -6.4008
Max Act: 6.0570. Min Act: -0.1700
Data Index: 7084506 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4008. Min Range: -6.4008
Max Act: 6.0258. Min Act: -0.1700
Data Index: 1020214 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4008. Min Range: -6.4008
Max Act: 5.9945. Min Act: -0.1700
Data Index: 7001829 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4008. Min Range: -6.4008
Max Act: 5.9945. Min Act: -0.1700
Data Index: 7058701 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4008. Min Range: -6.4008
Max Act: 5.9633. Min Act: -0.1700
Data Index: 1033216 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4008. Min Range: -6.4008
Max Act: 5.9633. Min Act: -0.1700
Data Index: 3492886 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4008. Min Range: -6.4008
Max Act: 5.9320. Min Act: -0.1700
Data Index: 5521644 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4008. Min Range: -6.4008
Max Act: 5.9008. Min Act: -0.1700
Data Index: 1784228 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4008. Min Range: -6.4008
Max Act: 5.9008. Min Act: -0.1700
Data Index: 1464180 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4008. Min Range: -6.4008
Max Act: 5.8695. Min Act: -0.1700
Data Index: 2117507 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19