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

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

Neuron 2551 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0369. Min Act: -0.0001

Data Index: 166183 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0343. Min Act: -0.0001

Data Index: 187224 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0311. Min Act: -0.0001

Data Index: 628895 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0306. Min Act: -0.0001

Data Index: 1326346 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0344. Min Act: -0.0001

Data Index: 71939 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0299. Min Act: -0.0001

Data Index: 255360 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0314. Min Act: -0.0001

Data Index: 416689 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0303. Min Act: -0.0001

Data Index: 1162894 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0313. Min Act: -0.0001

Data Index: 144785 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0296. Min Act: -0.0001

Data Index: 200877 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0288. Min Act: -0.0001

Data Index: 522537 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0285. Min Act: -0.0001

Data Index: 1335049 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0280. Min Act: -0.0001

Data Index: 203149 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1278983 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0281. Min Act: -0.0001

Data Index: 694259 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0256. Min Act: -0.0001

Data Index: 785475 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0299. Min Act: -0.0001

Data Index: 637032 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0278. Min Act: -0.0001

Data Index: 130065 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0286. Min Act: -0.0001

Data Index: 633483 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0280. Min Act: -0.0001

Data Index: 1115996 (C4 (Web Text))

Max Activating Token Index: 903