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

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

Neuron 4313 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0301. Min Act: -0.0001

Data Index: 335998 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0285. Min Act: -0.0001

Data Index: 90685 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0304. Min Act: -0.0001

Data Index: 644720 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0251. Min Act: -0.0000

Data Index: 1366795 (Python Code)

Max Activating Token Index: 412

Text #4

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0248. Min Act: -0.0000

Data Index: 1017918 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0254. Min Act: -0.0000

Data Index: 713008 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0247. Min Act: -0.0001

Data Index: 90062 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0254. Min Act: -0.0000

Data Index: 511011 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0250. Min Act: -0.0000

Data Index: 443478 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0215. Min Act: -0.0000

Data Index: 980142 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0228. Min Act: -0.0001

Data Index: 237926 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0247. Min Act: -0.0000

Data Index: 248373 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0234. Min Act: -0.0001

Data Index: 1050148 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0233. Min Act: -0.0000

Data Index: 1157542 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0232. Min Act: -0.0000

Data Index: 1429989 (Python Code)

Max Activating Token Index: 181

Text #15

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0221. Min Act: -0.0001

Data Index: 920811 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0248. Min Act: -0.0001

Data Index: 768100 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0228. Min Act: -0.0000

Data Index: 1603964 (Python Code)

Max Activating Token Index: 146

Text #18

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0210. Min Act: -0.0001

Data Index: 139686 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0206. Min Act: -0.0000

Data Index: 1070936 (C4 (Web Text))

Max Activating Token Index: 652