Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2228 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0415. Min Act: -0.0004

Data Index: 886119 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0351. Min Act: -0.0004

Data Index: 964944 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0382. Min Act: -0.0004

Data Index: 299170 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0385. Min Act: -0.0004

Data Index: 653738 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0356. Min Act: -0.0004

Data Index: 1014905 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0331. Min Act: -0.0004

Data Index: 1242538 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0236. Min Act: -0.0004

Data Index: 126513 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0361. Min Act: -0.0004

Data Index: 810002 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0321. Min Act: -0.0004

Data Index: 1234038 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0342. Min Act: -0.0004

Data Index: 714051 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0316. Min Act: -0.0004

Data Index: 1276373 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0328. Min Act: -0.0004

Data Index: 1194328 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0282. Min Act: -0.0004

Data Index: 1337131 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0339. Min Act: -0.0004

Data Index: 915553 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0319. Min Act: -0.0004

Data Index: 170810 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0381. Min Act: -0.0004

Data Index: 449919 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0382. Min Act: -0.0004

Data Index: 1357797 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0334. Min Act: -0.0004

Data Index: 1254273 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0361. Min Act: -0.0004

Data Index: 210142 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0343. Min Act: -0.0004

Data Index: 533866 (C4 (Web Text))

Max Activating Token Index: 786