Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1511 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8334. Min Range: -8.8334
Max Act: 8.8334. Min Act: -0.1700
Data Index: 5184548 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8334. Min Range: -8.8334
Max Act: 8.4584. Min Act: -0.1700
Data Index: 3387208 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8334. Min Range: -8.8334
Max Act: 8.5209. Min Act: -0.1700
Data Index: 4672352 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8334. Min Range: -8.8334
Max Act: 8.2709. Min Act: -0.1700
Data Index: 7190931 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8334. Min Range: -8.8334
Max Act: 8.3959. Min Act: -0.1700
Data Index: 1980742 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8334. Min Range: -8.8334
Max Act: 8.3334. Min Act: -0.1700
Data Index: 4519261 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8334. Min Range: -8.8334
Max Act: 8.3334. Min Act: -0.1700
Data Index: 5726024 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8334. Min Range: -8.8334
Max Act: 8.3334. Min Act: -0.1700
Data Index: 4268582 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8334. Min Range: -8.8334
Max Act: 8.2709. Min Act: -0.1700
Data Index: 1552306 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8334. Min Range: -8.8334
Max Act: 8.2084. Min Act: -0.1700
Data Index: 8648469 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8334. Min Range: -8.8334
Max Act: 8.1459. Min Act: -0.1700
Data Index: 1091293 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8334. Min Range: -8.8334
Max Act: 8.1459. Min Act: -0.1700
Data Index: 7736861 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8334. Min Range: -8.8334
Max Act: 8.1459. Min Act: -0.1700
Data Index: 1453838 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8334. Min Range: -8.8334
Max Act: 8.1459. Min Act: -0.1700
Data Index: 481711 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8334. Min Range: -8.8334
Max Act: 8.0834. Min Act: -0.1700
Data Index: 4805245 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8334. Min Range: -8.8334
Max Act: 8.0834. Min Act: -0.1700
Data Index: 5512627 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8334. Min Range: -8.8334
Max Act: 8.0834. Min Act: -0.1700
Data Index: 856182 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8334. Min Range: -8.8334
Max Act: 8.0834. Min Act: -0.1700
Data Index: 3732974 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8334. Min Range: -8.8334
Max Act: 8.0209. Min Act: -0.1700
Data Index: 3330081 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8334. Min Range: -8.8334
Max Act: 8.0209. Min Act: -0.1700
Data Index: 6430470 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19