Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3795 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0538. Min Range: -3.0538
Max Act: 3.0538. Min Act: -0.1700
Data Index: 3046778 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0538. Min Range: -3.0538
Max Act: 2.9590. Min Act: -0.1700
Data Index: 280285 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0538. Min Range: -3.0538
Max Act: 2.9590. Min Act: -0.1700
Data Index: 6097493 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0538. Min Range: -3.0538
Max Act: 2.8956. Min Act: -0.1700
Data Index: 6213946 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0538. Min Range: -3.0538
Max Act: 2.8798. Min Act: -0.1700
Data Index: 4242442 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0538. Min Range: -3.0538
Max Act: 2.8798. Min Act: -0.1700
Data Index: 3495881 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0538. Min Range: -3.0538
Max Act: 2.8639. Min Act: -0.1700
Data Index: 4195696 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0538. Min Range: -3.0538
Max Act: 2.8639. Min Act: -0.1700
Data Index: 6806122 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0538. Min Range: -3.0538
Max Act: 2.8798. Min Act: -0.1700
Data Index: 7575713 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0538. Min Range: -3.0538
Max Act: 2.8798. Min Act: -0.1700
Data Index: 8068083 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0538. Min Range: -3.0538
Max Act: 2.8480. Min Act: -0.1700
Data Index: 6093447 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0538. Min Range: -3.0538
Max Act: 2.8480. Min Act: -0.1700
Data Index: 4384359 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0538. Min Range: -3.0538
Max Act: 2.8162. Min Act: -0.1700
Data Index: 569076 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0538. Min Range: -3.0538
Max Act: 2.8480. Min Act: -0.1700
Data Index: 6580967 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0538. Min Range: -3.0538
Max Act: 2.8321. Min Act: -0.1700
Data Index: 4650774 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0538. Min Range: -3.0538
Max Act: 2.8321. Min Act: -0.1700
Data Index: 6409121 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0538. Min Range: -3.0538
Max Act: 2.8003. Min Act: -0.1700
Data Index: 7544234 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0538. Min Range: -3.0538
Max Act: 2.7844. Min Act: -0.1700
Data Index: 7561358 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0538. Min Range: -3.0538
Max Act: 2.8003. Min Act: -0.1700
Data Index: 2182837 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0538. Min Range: -3.0538
Max Act: 2.8003. Min Act: -0.1700
Data Index: 4010215 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19