Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 168 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0388. Min Act: -0.0005

Data Index: 300305 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0345. Min Act: -0.0005

Data Index: 193232 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0334. Min Act: -0.0005

Data Index: 537345 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0323. Min Act: -0.0005

Data Index: 1244350 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0311. Min Act: -0.0005

Data Index: 150264 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0312. Min Act: -0.0005

Data Index: 26100 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0306. Min Act: -0.0005

Data Index: 312345 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0317. Min Act: -0.0005

Data Index: 379041 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0299. Min Act: -0.0005

Data Index: 774225 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0300. Min Act: -0.0005

Data Index: 840345 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0298. Min Act: -0.0005

Data Index: 867491 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0279. Min Act: -0.0005

Data Index: 286043 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0287. Min Act: -0.0005

Data Index: 131128 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0283. Min Act: -0.0005

Data Index: 1205110 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0296. Min Act: -0.0005

Data Index: 875508 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0287. Min Act: -0.0005

Data Index: 846827 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0280. Min Act: -0.0005

Data Index: 658580 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0278. Min Act: -0.0005

Data Index: 1135918 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0289. Min Act: -0.0005

Data Index: 111526 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0277. Min Act: -0.0005

Data Index: 1375545 (Python Code)

Max Activating Token Index: 742