Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2910 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0502. Min Range: -2.0502

Max Act: 2.0502. Min Act: -0.0000

Data Index: 1179083 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 2.0502. Min Range: -2.0502

Max Act: 1.9935. Min Act: -0.0000

Data Index: 986753 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 2.0502. Min Range: -2.0502

Max Act: 1.8491. Min Act: -0.0000

Data Index: 1163756 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 2.0502. Min Range: -2.0502

Max Act: 1.9002. Min Act: -0.0000

Data Index: 890403 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 2.0502. Min Range: -2.0502

Max Act: 1.8180. Min Act: -0.0000

Data Index: 850592 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 2.0502. Min Range: -2.0502

Max Act: 1.7175. Min Act: -0.0000

Data Index: 1311192 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 2.0502. Min Range: -2.0502

Max Act: 1.9239. Min Act: -0.0000

Data Index: 629685 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 2.0502. Min Range: -2.0502

Max Act: 1.6343. Min Act: -0.0000

Data Index: 400267 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 2.0502. Min Range: -2.0502

Max Act: 1.5073. Min Act: -0.0000

Data Index: 557523 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 2.0502. Min Range: -2.0502

Max Act: 1.3903. Min Act: 0.0001

Data Index: 443884 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 2.0502. Min Range: -2.0502

Max Act: 1.5551. Min Act: -0.0000

Data Index: 328884 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 2.0502. Min Range: -2.0502

Max Act: 1.2311. Min Act: -0.0000

Data Index: 1056669 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 2.0502. Min Range: -2.0502

Max Act: 1.4402. Min Act: -0.0000

Data Index: 1008501 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 2.0502. Min Range: -2.0502

Max Act: 1.4385. Min Act: -0.0000

Data Index: 1184430 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 2.0502. Min Range: -2.0502

Max Act: 1.5049. Min Act: -0.0000

Data Index: 277346 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 2.0502. Min Range: -2.0502

Max Act: 1.2632. Min Act: -0.0000

Data Index: 115875 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 2.0502. Min Range: -2.0502

Max Act: 1.3208. Min Act: -0.0000

Data Index: 131884 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 2.0502. Min Range: -2.0502

Max Act: 1.3837. Min Act: -0.0000

Data Index: 1102393 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 2.0502. Min Range: -2.0502

Max Act: 1.3010. Min Act: -0.0000

Data Index: 528207 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 2.0502. Min Range: -2.0502

Max Act: 1.2692. Min Act: -0.0000

Data Index: 419013 (C4 (Web Text))

Max Activating Token Index: 957