Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2691 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5729. Min Range: -9.5729
Max Act: 9.5729. Min Act: -0.1700
Data Index: 5509688 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5729. Min Range: -9.5729
Max Act: 9.0729. Min Act: -0.1700
Data Index: 5559131 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5729. Min Range: -9.5729
Max Act: 8.8229. Min Act: -0.1700
Data Index: 1348564 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5729. Min Range: -9.5729
Max Act: 8.6979. Min Act: -0.1700
Data Index: 7441148 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5729. Min Range: -9.5729
Max Act: 8.6354. Min Act: -0.1700
Data Index: 1267165 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5729. Min Range: -9.5729
Max Act: 8.6354. Min Act: -0.1700
Data Index: 4948128 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5729. Min Range: -9.5729
Max Act: 8.5729. Min Act: -0.1700
Data Index: 5592578 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5729. Min Range: -9.5729
Max Act: 8.5729. Min Act: -0.1700
Data Index: 6535588 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5729. Min Range: -9.5729
Max Act: 8.4479. Min Act: -0.1700
Data Index: 2177483 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5729. Min Range: -9.5729
Max Act: 8.4479. Min Act: -0.1700
Data Index: 7505101 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5729. Min Range: -9.5729
Max Act: 8.4479. Min Act: -0.1700
Data Index: 6308125 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5729. Min Range: -9.5729
Max Act: 8.4479. Min Act: -0.1700
Data Index: 8767164 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5729. Min Range: -9.5729
Max Act: 8.3229. Min Act: -0.1700
Data Index: 5229398 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5729. Min Range: -9.5729
Max Act: 8.2604. Min Act: -0.1700
Data Index: 8748986 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5729. Min Range: -9.5729
Max Act: 8.3229. Min Act: -0.1700
Data Index: 4505485 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5729. Min Range: -9.5729
Max Act: 8.2604. Min Act: -0.1700
Data Index: 4201204 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5729. Min Range: -9.5729
Max Act: 8.1979. Min Act: -0.1700
Data Index: 4930464 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5729. Min Range: -9.5729
Max Act: 8.2604. Min Act: -0.1700
Data Index: 5535879 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5729. Min Range: -9.5729
Max Act: 8.1979. Min Act: -0.1700
Data Index: 6336849 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5729. Min Range: -9.5729
Max Act: 8.1979. Min Act: -0.1700
Data Index: 3171116 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19