Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2808 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.0654. Min Range: -4.0654
Max Act: 4.0654. Min Act: -0.0001
Data Index: 407174 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.4264. Min Act: -0.0001
Data Index: 554656 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.2506. Min Act: -0.0001
Data Index: 1086491 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.1355. Min Act: -0.0001
Data Index: 906767 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0654. Min Range: -4.0654
Max Act: 2.7607. Min Act: -0.0001
Data Index: 702363 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0654. Min Range: -4.0654
Max Act: 3.0488. Min Act: -0.0001
Data Index: 150235 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0654. Min Range: -4.0654
Max Act: 2.8865. Min Act: -0.0001
Data Index: 287376 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0654. Min Range: -4.0654
Max Act: 2.5580. Min Act: -0.0001
Data Index: 1227814 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0654. Min Range: -4.0654
Max Act: 2.2198. Min Act: -0.0001
Data Index: 126822 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0654. Min Range: -4.0654
Max Act: 2.3185. Min Act: -0.0000
Data Index: 749778 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0654. Min Range: -4.0654
Max Act: 2.2571. Min Act: -0.0001
Data Index: 452986 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0654. Min Range: -4.0654
Max Act: 2.3474. Min Act: -0.0001
Data Index: 65843 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0654. Min Range: -4.0654
Max Act: 2.2224. Min Act: -0.0001
Data Index: 355127 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0654. Min Range: -4.0654
Max Act: 2.3107. Min Act: -0.0001
Data Index: 82565 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0654. Min Range: -4.0654
Max Act: 2.2481. Min Act: -0.0001
Data Index: 1296059 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0654. Min Range: -4.0654
Max Act: 2.1102. Min Act: -0.0001
Data Index: 1075723 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0654. Min Range: -4.0654
Max Act: 1.8843. Min Act: -0.0001
Data Index: 340847 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0654. Min Range: -4.0654
Max Act: 1.5673. Min Act: -0.0001
Data Index: 937622 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0654. Min Range: -4.0654
Max Act: 1.9861. Min Act: -0.0001
Data Index: 222925 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0654. Min Range: -4.0654
Max Act: 1.9729. Min Act: -0.0001
Data Index: 214688 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19