Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2253 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1610. Min Act: -0.0001

Data Index: 231021 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1680. Min Act: -0.0001

Data Index: 647264 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1611. Min Act: -0.0001

Data Index: 1000458 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1389. Min Act: -0.0001

Data Index: 210736 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1356. Min Act: -0.0000

Data Index: 1094327 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1328. Min Act: -0.0000

Data Index: 772645 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1302. Min Act: -0.0001

Data Index: 115521 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1296. Min Act: -0.0001

Data Index: 808342 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1330. Min Act: -0.0001

Data Index: 1192878 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1320. Min Act: -0.0001

Data Index: 1028460 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1273. Min Act: -0.0001

Data Index: 1086896 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1273. Min Act: -0.0001

Data Index: 1340415 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1274. Min Act: -0.0001

Data Index: 663273 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1261. Min Act: -0.0000

Data Index: 91787 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1254. Min Act: -0.0000

Data Index: 499106 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1300. Min Act: -0.0000

Data Index: 942977 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1111. Min Act: -0.0001

Data Index: 223442 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1242. Min Act: -0.0001

Data Index: 30976 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1276. Min Act: -0.0001

Data Index: 41022 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1228. Min Act: -0.0001

Data Index: 124644 (C4 (Web Text))

Max Activating Token Index: 765