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

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

Neuron 826 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: 0.2568. Min Range: -0.2568

Max Act: 0.2395. Min Act: -0.0000

Data Index: 1631089 (Python Code)

Max Activating Token Index: 977

Text #1

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2568. Min Act: -0.0000

Data Index: 909872 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2314. Min Act: -0.0000

Data Index: 1399328 (Python Code)

Max Activating Token Index: 331

Text #3

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2307. Min Act: -0.0000

Data Index: 1514257 (Python Code)

Max Activating Token Index: 349

Text #4

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2431. Min Act: -0.0000

Data Index: 1566440 (Python Code)

Max Activating Token Index: 703

Text #5

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2266. Min Act: -0.0000

Data Index: 1622155 (Python Code)

Max Activating Token Index: 786

Text #6

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2260. Min Act: -0.0000

Data Index: 1610154 (Python Code)

Max Activating Token Index: 552

Text #7

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1404838 (Python Code)

Max Activating Token Index: 62

Text #8

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1547965 (Python Code)

Max Activating Token Index: 241

Text #9

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2315. Min Act: -0.0000

Data Index: 1279531 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2311. Min Act: -0.0000

Data Index: 689614 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2484. Min Act: -0.0000

Data Index: 187921 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2366. Min Act: -0.0000

Data Index: 365376 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1607846 (Python Code)

Max Activating Token Index: 173

Text #14

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1264272 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2209. Min Act: -0.0000

Data Index: 39283 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2055. Min Act: -0.0000

Data Index: 383962 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2142. Min Act: -0.0000

Data Index: 902366 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2199. Min Act: -0.0000

Data Index: 513165 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2133. Min Act: -0.0000

Data Index: 140493 (C4 (Web Text))

Max Activating Token Index: 916