Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2423 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3392. Min Range: -5.3392
Max Act: 5.3392. Min Act: -0.1700
Data Index: 4623860 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3392. Min Range: -5.3392
Max Act: 5.2142. Min Act: -0.1700
Data Index: 7418638 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3392. Min Range: -5.3392
Max Act: 5.2455. Min Act: -0.1700
Data Index: 6422423 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3392. Min Range: -5.3392
Max Act: 5.1205. Min Act: -0.1700
Data Index: 7436509 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3392. Min Range: -5.3392
Max Act: 5.1205. Min Act: -0.1700
Data Index: 2779021 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3392. Min Range: -5.3392
Max Act: 5.0892. Min Act: -0.1700
Data Index: 4717586 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3392. Min Range: -5.3392
Max Act: 5.0267. Min Act: -0.1700
Data Index: 7576470 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3392. Min Range: -5.3392
Max Act: 4.9955. Min Act: -0.1700
Data Index: 6434528 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3392. Min Range: -5.3392
Max Act: 4.9955. Min Act: -0.1700
Data Index: 955014 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3392. Min Range: -5.3392
Max Act: 4.9642. Min Act: -0.1700
Data Index: 8239919 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3392. Min Range: -5.3392
Max Act: 4.9642. Min Act: -0.1700
Data Index: 2966697 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3392. Min Range: -5.3392
Max Act: 4.9955. Min Act: -0.1700
Data Index: 6847621 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3392. Min Range: -5.3392
Max Act: 4.9330. Min Act: -0.1700
Data Index: 70824 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3392. Min Range: -5.3392
Max Act: 4.9330. Min Act: -0.1700
Data Index: 7403224 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3392. Min Range: -5.3392
Max Act: 4.9017. Min Act: -0.1700
Data Index: 3005315 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3392. Min Range: -5.3392
Max Act: 4.8705. Min Act: -0.1700
Data Index: 4750589 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3392. Min Range: -5.3392
Max Act: 4.9017. Min Act: -0.1700
Data Index: 7567627 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3392. Min Range: -5.3392
Max Act: 4.9017. Min Act: -0.1700
Data Index: 886413 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3392. Min Range: -5.3392
Max Act: 4.9017. Min Act: -0.1700
Data Index: 5825356 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3392. Min Range: -5.3392
Max Act: 4.9330. Min Act: -0.1700
Data Index: 1098578 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19