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

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

Neuron 1200 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.3177. Min Act: -0.0001

Data Index: 335245 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2887. Min Act: -0.0001

Data Index: 253244 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2838. Min Act: -0.0001

Data Index: 1101015 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2552. Min Act: -0.0001

Data Index: 1641092 (Python Code)

Max Activating Token Index: 312

Text #4

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2618. Min Act: -0.0001

Data Index: 993645 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2517. Min Act: -0.0001

Data Index: 1000631 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2228. Min Act: -0.0001

Data Index: 538277 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2481. Min Act: -0.0001

Data Index: 1378481 (Python Code)

Max Activating Token Index: 422

Text #8

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2199. Min Act: -0.0001

Data Index: 102324 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2307. Min Act: -0.0001

Data Index: 280442 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2389. Min Act: -0.0001

Data Index: 1145191 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2166. Min Act: -0.0001

Data Index: 1101912 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2172. Min Act: -0.0001

Data Index: 1518576 (Python Code)

Max Activating Token Index: 676

Text #13

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2112. Min Act: -0.0001

Data Index: 1481460 (Python Code)

Max Activating Token Index: 259

Text #14

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2166. Min Act: -0.0001

Data Index: 769173 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2275. Min Act: -0.0001

Data Index: 600926 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2230. Min Act: -0.0001

Data Index: 479735 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2228. Min Act: -0.0001

Data Index: 1632272 (Python Code)

Max Activating Token Index: 573

Text #18

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2068. Min Act: -0.0001

Data Index: 615027 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2164. Min Act: -0.0001

Data Index: 99958 (C4 (Web Text))

Max Activating Token Index: 43