Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 12 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0310. Min Act: -0.0001

Data Index: 715186 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0316. Min Act: -0.0001

Data Index: 985933 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0269. Min Act: -0.0001

Data Index: 1202939 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0276. Min Act: -0.0001

Data Index: 782691 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0268. Min Act: -0.0001

Data Index: 837878 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0267. Min Act: -0.0001

Data Index: 907648 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0261. Min Act: -0.0001

Data Index: 718906 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0256. Min Act: -0.0001

Data Index: 568820 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0244. Min Act: -0.0001

Data Index: 800639 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0238. Min Act: -0.0001

Data Index: 1024450 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0233. Min Act: -0.0001

Data Index: 919178 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0241. Min Act: -0.0001

Data Index: 1078274 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0236. Min Act: -0.0001

Data Index: 350040 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0232. Min Act: -0.0001

Data Index: 699284 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0242. Min Act: -0.0001

Data Index: 45819 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0237. Min Act: -0.0001

Data Index: 453671 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0246. Min Act: -0.0001

Data Index: 1073030 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0233. Min Act: -0.0001

Data Index: 755286 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0227. Min Act: -0.0001

Data Index: 493289 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0234. Min Act: -0.0001

Data Index: 1255289 (C4 (Web Text))

Max Activating Token Index: 154