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

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

Neuron 2659 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0484. Min Act: -0.0001

Data Index: 926749 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0429. Min Act: -0.0001

Data Index: 1655107 (Python Code)

Max Activating Token Index: 777

Text #2

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0374. Min Act: -0.0001

Data Index: 206023 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0347. Min Act: -0.0001

Data Index: 128112 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0342. Min Act: -0.0001

Data Index: 1180476 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0346. Min Act: -0.0001

Data Index: 76821 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0325. Min Act: -0.0001

Data Index: 1422963 (Python Code)

Max Activating Token Index: 302

Text #7

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0271. Min Act: -0.0001

Data Index: 1487710 (Python Code)

Max Activating Token Index: 786

Text #8

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0293. Min Act: -0.0001

Data Index: 977988 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0290. Min Act: -0.0001

Data Index: 1438221 (Python Code)

Max Activating Token Index: 47

Text #10

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0283. Min Act: -0.0001

Data Index: 878422 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0269. Min Act: -0.0001

Data Index: 1162243 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0274. Min Act: -0.0001

Data Index: 1235217 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0282. Min Act: -0.0001

Data Index: 434481 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0284. Min Act: -0.0001

Data Index: 470199 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0283. Min Act: -0.0001

Data Index: 199637 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0303. Min Act: -0.0001

Data Index: 887798 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0299. Min Act: -0.0001

Data Index: 326532 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0282. Min Act: -0.0001

Data Index: 766166 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0283. Min Act: -0.0001

Data Index: 1640091 (Python Code)

Max Activating Token Index: 157