Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 604 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9210. Min Range: -5.9210
Max Act: 5.9210. Min Act: -0.1700
Data Index: 4108034 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9210. Min Range: -5.9210
Max Act: 5.8273. Min Act: -0.1700
Data Index: 4683975 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9210. Min Range: -5.9210
Max Act: 5.6398. Min Act: -0.1700
Data Index: 4425766 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9210. Min Range: -5.9210
Max Act: 5.5460. Min Act: -0.1700
Data Index: 2295231 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9210. Min Range: -5.9210
Max Act: 5.4835. Min Act: -0.1700
Data Index: 255686 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9210. Min Range: -5.9210
Max Act: 5.4835. Min Act: -0.1700
Data Index: 3703849 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9210. Min Range: -5.9210
Max Act: 5.4523. Min Act: -0.1700
Data Index: 7218770 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9210. Min Range: -5.9210
Max Act: 5.4835. Min Act: -0.1700
Data Index: 2908688 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9210. Min Range: -5.9210
Max Act: 5.3898. Min Act: -0.1700
Data Index: 1730025 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9210. Min Range: -5.9210
Max Act: 5.2648. Min Act: -0.1700
Data Index: 4868147 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9210. Min Range: -5.9210
Max Act: 5.2648. Min Act: -0.1700
Data Index: 6334765 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9210. Min Range: -5.9210
Max Act: 5.2335. Min Act: -0.1700
Data Index: 6957840 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9210. Min Range: -5.9210
Max Act: 5.2023. Min Act: -0.1700
Data Index: 5156689 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9210. Min Range: -5.9210
Max Act: 5.2335. Min Act: -0.1700
Data Index: 57464 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9210. Min Range: -5.9210
Max Act: 5.2335. Min Act: -0.1700
Data Index: 197777 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9210. Min Range: -5.9210
Max Act: 5.2648. Min Act: -0.1700
Data Index: 4108037 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9210. Min Range: -5.9210
Max Act: 5.2023. Min Act: -0.1700
Data Index: 497414 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9210. Min Range: -5.9210
Max Act: 5.2023. Min Act: -0.1700
Data Index: 7664395 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9210. Min Range: -5.9210
Max Act: 5.1710. Min Act: -0.1700
Data Index: 4832536 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9210. Min Range: -5.9210
Max Act: 5.2023. Min Act: -0.1700
Data Index: 2834037 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19