Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3672 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2530. Min Range: -3.2530
Max Act: 3.2530. Min Act: -0.1700
Data Index: 7262223 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2530. Min Range: -3.2530
Max Act: 3.1901. Min Act: -0.1700
Data Index: 1175226 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2530. Min Range: -3.2530
Max Act: 3.1744. Min Act: -0.1700
Data Index: 8583789 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2530. Min Range: -3.2530
Max Act: 3.1114. Min Act: -0.1700
Data Index: 4136780 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2530. Min Range: -3.2530
Max Act: 3.1429. Min Act: -0.1700
Data Index: 4669644 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2530. Min Range: -3.2530
Max Act: 3.1114. Min Act: -0.1700
Data Index: 3306515 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2530. Min Range: -3.2530
Max Act: 3.1272. Min Act: -0.1700
Data Index: 7641044 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2530. Min Range: -3.2530
Max Act: 3.0956. Min Act: -0.1700
Data Index: 2083685 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2530. Min Range: -3.2530
Max Act: 3.1114. Min Act: -0.1700
Data Index: 3937452 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2530. Min Range: -3.2530
Max Act: 3.1114. Min Act: -0.1700
Data Index: 4324149 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2530. Min Range: -3.2530
Max Act: 3.0956. Min Act: -0.1700
Data Index: 1877302 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2530. Min Range: -3.2530
Max Act: 3.1114. Min Act: -0.1700
Data Index: 7222018 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2530. Min Range: -3.2530
Max Act: 3.0956. Min Act: -0.1700
Data Index: 728283 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2530. Min Range: -3.2530
Max Act: 3.0799. Min Act: -0.1700
Data Index: 3182378 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2530. Min Range: -3.2530
Max Act: 3.0799. Min Act: -0.1700
Data Index: 8219496 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2530. Min Range: -3.2530
Max Act: 3.0956. Min Act: -0.1700
Data Index: 7690919 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2530. Min Range: -3.2530
Max Act: 3.0799. Min Act: -0.1700
Data Index: 671907 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2530. Min Range: -3.2530
Max Act: 3.0799. Min Act: -0.1700
Data Index: 8695797 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2530. Min Range: -3.2530
Max Act: 3.0641. Min Act: -0.1700
Data Index: 4236425 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2530. Min Range: -3.2530
Max Act: 3.0641. Min Act: -0.1700
Data Index: 7548637 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19