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

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

Neuron 387 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0290. Min Act: -0.0003

Data Index: 977533 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1161815 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0273. Min Act: -0.0003

Data Index: 16423 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0274. Min Act: -0.0003

Data Index: 466281 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0268. Min Act: -0.0003

Data Index: 772804 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0269. Min Act: -0.0003

Data Index: 354911 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0252. Min Act: -0.0002

Data Index: 452666 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0242. Min Act: -0.0002

Data Index: 1284551 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0245. Min Act: -0.0003

Data Index: 288699 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0240. Min Act: -0.0003

Data Index: 655631 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1276291 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0234. Min Act: -0.0003

Data Index: 207563 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0233. Min Act: -0.0003

Data Index: 668952 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0224. Min Act: -0.0002

Data Index: 93774 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0231. Min Act: -0.0003

Data Index: 496625 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0226. Min Act: -0.0003

Data Index: 467833 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0231. Min Act: -0.0003

Data Index: 493910 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0257. Min Act: -0.0003

Data Index: 147132 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1327478 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0214. Min Act: -0.0003

Data Index: 939047 (C4 (Web Text))

Max Activating Token Index: 133