Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1891 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4301. Min Range: -2.4301

Max Act: 2.4301. Min Act: -0.0000

Data Index: 200676 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 2.4301. Min Range: -2.4301

Max Act: 2.0590. Min Act: -0.0000

Data Index: 393092 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 2.4301. Min Range: -2.4301

Max Act: 2.1091. Min Act: -0.0000

Data Index: 391824 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 2.4301. Min Range: -2.4301

Max Act: 1.9631. Min Act: -0.0000

Data Index: 98168 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 2.4301. Min Range: -2.4301

Max Act: 1.5998. Min Act: -0.0000

Data Index: 501643 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 2.4301. Min Range: -2.4301

Max Act: 1.7892. Min Act: -0.0000

Data Index: 320273 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 2.4301. Min Range: -2.4301

Max Act: 1.7435. Min Act: -0.0000

Data Index: 1285280 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 2.4301. Min Range: -2.4301

Max Act: 1.6537. Min Act: -0.0000

Data Index: 1186495 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 2.4301. Min Range: -2.4301

Max Act: 1.7306. Min Act: -0.0000

Data Index: 1260318 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 2.4301. Min Range: -2.4301

Max Act: 1.7456. Min Act: -0.0000

Data Index: 764405 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 2.4301. Min Range: -2.4301

Max Act: 1.6575. Min Act: -0.0000

Data Index: 939413 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 2.4301. Min Range: -2.4301

Max Act: 1.4160. Min Act: -0.0000

Data Index: 464308 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 2.4301. Min Range: -2.4301

Max Act: 1.6362. Min Act: -0.0000

Data Index: 690893 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 2.4301. Min Range: -2.4301

Max Act: 1.5431. Min Act: -0.0000

Data Index: 532042 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 2.4301. Min Range: -2.4301

Max Act: 1.6739. Min Act: -0.0000

Data Index: 1545403 (Python Code)

Max Activating Token Index: 883

Text #15

Max Range: 2.4301. Min Range: -2.4301

Max Act: 1.6251. Min Act: -0.0000

Data Index: 1058236 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 2.4301. Min Range: -2.4301

Max Act: 1.6272. Min Act: -0.0000

Data Index: 770596 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 2.4301. Min Range: -2.4301

Max Act: 1.7112. Min Act: -0.0000

Data Index: 167876 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 2.4301. Min Range: -2.4301

Max Act: 1.5347. Min Act: -0.0000

Data Index: 52736 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 2.4301. Min Range: -2.4301

Max Act: 1.6885. Min Act: -0.0000

Data Index: 103499 (C4 (Web Text))

Max Activating Token Index: 590