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

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

Neuron 2173 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0403. Min Act: -0.0003

Data Index: 1134630 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0331. Min Act: -0.0003

Data Index: 1122747 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0339. Min Act: -0.0003

Data Index: 1017964 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0321. Min Act: -0.0003

Data Index: 705861 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0320. Min Act: -0.0003

Data Index: 122309 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0296. Min Act: -0.0003

Data Index: 476937 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0291. Min Act: -0.0003

Data Index: 331452 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0279. Min Act: -0.0003

Data Index: 821115 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0282. Min Act: -0.0003

Data Index: 27393 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1208262 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0270. Min Act: -0.0003

Data Index: 952192 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0282. Min Act: -0.0003

Data Index: 456654 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0273. Min Act: -0.0003

Data Index: 938150 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0269. Min Act: -0.0003

Data Index: 302431 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0268. Min Act: -0.0003

Data Index: 1011190 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0262. Min Act: -0.0003

Data Index: 312715 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0257. Min Act: -0.0003

Data Index: 90436 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0252. Min Act: -0.0003

Data Index: 268682 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0257. Min Act: -0.0003

Data Index: 878140 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0262. Min Act: -0.0003

Data Index: 156068 (C4 (Web Text))

Max Activating Token Index: 820