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

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

Neuron 2301 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0382. Min Act: -0.0001

Data Index: 773804 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1297388 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0365. Min Act: -0.0001

Data Index: 404946 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1081661 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0282. Min Act: -0.0001

Data Index: 114451 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1303685 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0278. Min Act: -0.0001

Data Index: 500753 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0289. Min Act: -0.0001

Data Index: 1128959 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0267. Min Act: -0.0001

Data Index: 383259 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0262. Min Act: -0.0001

Data Index: 640342 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0273. Min Act: -0.0001

Data Index: 477408 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0222. Min Act: -0.0001

Data Index: 1152029 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0250. Min Act: -0.0001

Data Index: 65616 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0240. Min Act: -0.0001

Data Index: 1195220 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0259. Min Act: -0.0001

Data Index: 1359691 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0245. Min Act: -0.0001

Data Index: 1148556 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0227. Min Act: -0.0001

Data Index: 918809 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0256. Min Act: -0.0001

Data Index: 489691 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0225. Min Act: -0.0001

Data Index: 312595 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0253. Min Act: -0.0001

Data Index: 244925 (C4 (Web Text))

Max Activating Token Index: 717