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

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

Neuron 3329 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2625. Min Act: -0.0002

Data Index: 890658 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2422. Min Act: -0.0002

Data Index: 536165 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2435. Min Act: -0.0002

Data Index: 288227 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2378. Min Act: -0.0002

Data Index: 962020 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2451. Min Act: -0.0002

Data Index: 1152254 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2355. Min Act: -0.0002

Data Index: 229449 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2314. Min Act: -0.0002

Data Index: 431911 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2368. Min Act: -0.0002

Data Index: 594181 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2237. Min Act: -0.0002

Data Index: 941261 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2294. Min Act: -0.0002

Data Index: 848393 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2227. Min Act: -0.0002

Data Index: 446868 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2213. Min Act: -0.0002

Data Index: 191465 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2196. Min Act: -0.0002

Data Index: 869029 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2280. Min Act: -0.0002

Data Index: 554606 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2125. Min Act: -0.0002

Data Index: 887731 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2150. Min Act: -0.0002

Data Index: 1098315 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2232. Min Act: -0.0002

Data Index: 1143617 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2137. Min Act: -0.0002

Data Index: 520569 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2140. Min Act: -0.0002

Data Index: 434858 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2125. Min Act: -0.0002

Data Index: 418494 (C4 (Web Text))

Max Activating Token Index: 590