Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5781 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0299. Min Act: -0.0002

Data Index: 846537 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0280. Min Act: -0.0002

Data Index: 122769 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0282. Min Act: -0.0002

Data Index: 761607 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1255884 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1341692 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1626841 (Python Code)

Max Activating Token Index: 270

Text #6

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0271. Min Act: -0.0002

Data Index: 927771 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1124475 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0243. Min Act: -0.0002

Data Index: 852031 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0250. Min Act: -0.0002

Data Index: 97502 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0256. Min Act: -0.0002

Data Index: 122003 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0242. Min Act: -0.0002

Data Index: 1307159 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0240. Min Act: -0.0002

Data Index: 432362 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0237. Min Act: -0.0002

Data Index: 846814 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0237. Min Act: -0.0002

Data Index: 411791 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1589053 (Python Code)

Max Activating Token Index: 25

Text #16

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0233. Min Act: -0.0002

Data Index: 257155 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0236. Min Act: -0.0002

Data Index: 225559 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1053690 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1286124 (C4 (Web Text))

Max Activating Token Index: 139