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

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

Neuron 4956 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1666. Min Act: -0.0000

Data Index: 506028 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1586. Min Act: -0.0000

Data Index: 1356363 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1667. Min Act: -0.0000

Data Index: 600198 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1383. Min Act: -0.0000

Data Index: 905062 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1427. Min Act: -0.0000

Data Index: 482073 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1364. Min Act: -0.0000

Data Index: 1051677 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1326. Min Act: -0.0000

Data Index: 649734 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1250. Min Act: -0.0000

Data Index: 730044 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1238. Min Act: -0.0000

Data Index: 552632 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1296. Min Act: -0.0000

Data Index: 463191 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1221. Min Act: -0.0000

Data Index: 1243730 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1199. Min Act: -0.0000

Data Index: 739874 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1195. Min Act: -0.0000

Data Index: 789150 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1010. Min Act: -0.0000

Data Index: 171545 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1229. Min Act: -0.0000

Data Index: 1102682 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1176. Min Act: -0.0000

Data Index: 902763 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1144. Min Act: -0.0000

Data Index: 353006 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1217. Min Act: -0.0000

Data Index: 1285976 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1208. Min Act: -0.0000

Data Index: 1107126 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1126. Min Act: -0.0000

Data Index: 197544 (C4 (Web Text))

Max Activating Token Index: 672