Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1329 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0755. Min Range: -4.0755
Max Act: 4.0755. Min Act: -0.1700
Data Index: 8029245 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0755. Min Range: -4.0755
Max Act: 3.9504. Min Act: -0.1700
Data Index: 6701790 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0755. Min Range: -4.0755
Max Act: 3.9348. Min Act: -0.1700
Data Index: 6819656 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0755. Min Range: -4.0755
Max Act: 3.9035. Min Act: -0.1700
Data Index: 1072136 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0755. Min Range: -4.0755
Max Act: 3.8723. Min Act: -0.1700
Data Index: 2475789 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0755. Min Range: -4.0755
Max Act: 3.8566. Min Act: -0.1700
Data Index: 8165962 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0755. Min Range: -4.0755
Max Act: 3.8723. Min Act: -0.1700
Data Index: 4965801 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0755. Min Range: -4.0755
Max Act: 3.8723. Min Act: -0.1700
Data Index: 4356518 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0755. Min Range: -4.0755
Max Act: 3.8879. Min Act: -0.1700
Data Index: 4853634 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0755. Min Range: -4.0755
Max Act: 3.8566. Min Act: -0.1700
Data Index: 5823320 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0755. Min Range: -4.0755
Max Act: 3.8097. Min Act: -0.1700
Data Index: 7456365 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0755. Min Range: -4.0755
Max Act: 3.7784. Min Act: -0.1700
Data Index: 4651871 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0755. Min Range: -4.0755
Max Act: 3.7784. Min Act: -0.1700
Data Index: 2615279 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0755. Min Range: -4.0755
Max Act: 3.7784. Min Act: -0.1700
Data Index: 440400 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0755. Min Range: -4.0755
Max Act: 3.7784. Min Act: -0.1700
Data Index: 647442 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0755. Min Range: -4.0755
Max Act: 3.7472. Min Act: -0.1700
Data Index: 2254181 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0755. Min Range: -4.0755
Max Act: 3.7159. Min Act: -0.1700
Data Index: 5348299 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0755. Min Range: -4.0755
Max Act: 3.7472. Min Act: -0.1700
Data Index: 7496886 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0755. Min Range: -4.0755
Max Act: 3.7315. Min Act: -0.1700
Data Index: 1204852 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0755. Min Range: -4.0755
Max Act: 3.7315. Min Act: -0.1700
Data Index: 2611247 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19