Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2397 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8389. Min Range: -6.8389
Max Act: 6.8389. Min Act: -0.1700
Data Index: 1580590 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8389. Min Range: -6.8389
Max Act: 6.6202. Min Act: -0.1700
Data Index: 3305946 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8389. Min Range: -6.8389
Max Act: 6.6514. Min Act: -0.1700
Data Index: 8500712 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8389. Min Range: -6.8389
Max Act: 6.5889. Min Act: -0.1700
Data Index: 1379572 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8389. Min Range: -6.8389
Max Act: 6.5889. Min Act: -0.1700
Data Index: 5213829 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8389. Min Range: -6.8389
Max Act: 6.5264. Min Act: -0.1700
Data Index: 1947160 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8389. Min Range: -6.8389
Max Act: 6.5889. Min Act: -0.1700
Data Index: 561617 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8389. Min Range: -6.8389
Max Act: 6.5264. Min Act: -0.1700
Data Index: 1340882 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8389. Min Range: -6.8389
Max Act: 6.5264. Min Act: -0.1700
Data Index: 5162641 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8389. Min Range: -6.8389
Max Act: 6.4952. Min Act: -0.1700
Data Index: 6118115 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8389. Min Range: -6.8389
Max Act: 6.4639. Min Act: -0.1700
Data Index: 1008356 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8389. Min Range: -6.8389
Max Act: 6.4639. Min Act: -0.1700
Data Index: 8621848 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8389. Min Range: -6.8389
Max Act: 6.4639. Min Act: -0.1700
Data Index: 7370986 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8389. Min Range: -6.8389
Max Act: 6.4639. Min Act: -0.1700
Data Index: 4730616 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8389. Min Range: -6.8389
Max Act: 6.4327. Min Act: -0.1700
Data Index: 4331910 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8389. Min Range: -6.8389
Max Act: 6.4014. Min Act: -0.1700
Data Index: 7300928 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8389. Min Range: -6.8389
Max Act: 6.4014. Min Act: -0.1700
Data Index: 1321810 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8389. Min Range: -6.8389
Max Act: 6.3077. Min Act: -0.1700
Data Index: 7700342 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8389. Min Range: -6.8389
Max Act: 6.2764. Min Act: -0.1700
Data Index: 4279882 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8389. Min Range: -6.8389
Max Act: 6.3389. Min Act: -0.1700
Data Index: 4500659 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19