Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3742 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7510. Min Range: -6.7510
Max Act: 6.7510. Min Act: -0.1700
Data Index: 4165757 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7510. Min Range: -6.7510
Max Act: 6.6885. Min Act: -0.1700
Data Index: 2138766 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7510. Min Range: -6.7510
Max Act: 6.6885. Min Act: -0.1700
Data Index: 8386038 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7510. Min Range: -6.7510
Max Act: 6.6572. Min Act: -0.1700
Data Index: 5839343 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7510. Min Range: -6.7510
Max Act: 6.6572. Min Act: -0.1700
Data Index: 889904 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7510. Min Range: -6.7510
Max Act: 6.6260. Min Act: -0.1700
Data Index: 8394261 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7510. Min Range: -6.7510
Max Act: 6.6260. Min Act: -0.1700
Data Index: 5702390 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7510. Min Range: -6.7510
Max Act: 6.5947. Min Act: -0.1700
Data Index: 5173080 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7510. Min Range: -6.7510
Max Act: 6.5947. Min Act: -0.1700
Data Index: 4107612 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7510. Min Range: -6.7510
Max Act: 6.5635. Min Act: -0.1700
Data Index: 3915286 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7510. Min Range: -6.7510
Max Act: 6.5635. Min Act: -0.1700
Data Index: 850288 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7510. Min Range: -6.7510
Max Act: 6.5635. Min Act: -0.1700
Data Index: 6306627 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7510. Min Range: -6.7510
Max Act: 6.5322. Min Act: -0.1700
Data Index: 3410510 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7510. Min Range: -6.7510
Max Act: 6.5322. Min Act: -0.1700
Data Index: 8622783 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7510. Min Range: -6.7510
Max Act: 6.5322. Min Act: -0.1700
Data Index: 596703 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7510. Min Range: -6.7510
Max Act: 6.5010. Min Act: -0.1700
Data Index: 5298075 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7510. Min Range: -6.7510
Max Act: 6.5635. Min Act: -0.1700
Data Index: 7131312 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7510. Min Range: -6.7510
Max Act: 6.5635. Min Act: -0.1700
Data Index: 6542085 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7510. Min Range: -6.7510
Max Act: 6.5010. Min Act: -0.1700
Data Index: 2374975 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7510. Min Range: -6.7510
Max Act: 6.4697. Min Act: -0.1700
Data Index: 1265527 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19