Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 591 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.7394. Min Act: -0.0001

Data Index: 5317 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.7162. Min Act: -0.0000

Data Index: 306091 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.6611. Min Act: -0.0001

Data Index: 89303 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.6274. Min Act: -0.0001

Data Index: 138432 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.6476. Min Act: -0.0000

Data Index: 42136 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.6336. Min Act: -0.0000

Data Index: 1039989 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.6190. Min Act: -0.0000

Data Index: 830750 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.6069. Min Act: -0.0000

Data Index: 1228863 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.6163. Min Act: -0.0000

Data Index: 297655 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.5877. Min Act: -0.0001

Data Index: 868218 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1334294 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.5893. Min Act: -0.0001

Data Index: 793328 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.5688. Min Act: -0.0001

Data Index: 708998 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.5691. Min Act: -0.0001

Data Index: 1144211 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.5789. Min Act: -0.0000

Data Index: 323990 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1079369 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.5690. Min Act: -0.0000

Data Index: 878329 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.5631. Min Act: -0.0001

Data Index: 638659 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1034139 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.5371. Min Act: -0.0000

Data Index: 815881 (C4 (Web Text))

Max Activating Token Index: 981