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

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

Neuron 2422 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4426. Min Range: -4.4426

Max Act: 4.4426. Min Act: -0.0000

Data Index: 1181616 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 4.4426. Min Range: -4.4426

Max Act: 3.8177. Min Act: -0.0000

Data Index: 703927 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 4.4426. Min Range: -4.4426

Max Act: 3.9984. Min Act: -0.0000

Data Index: 22785 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 4.4426. Min Range: -4.4426

Max Act: 4.0615. Min Act: -0.0000

Data Index: 772510 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 4.4426. Min Range: -4.4426

Max Act: 3.5998. Min Act: -0.0000

Data Index: 175283 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 4.4426. Min Range: -4.4426

Max Act: 3.6378. Min Act: -0.0000

Data Index: 791591 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 4.4426. Min Range: -4.4426

Max Act: 2.8301. Min Act: -0.0000

Data Index: 701086 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 4.4426. Min Range: -4.4426

Max Act: 3.1795. Min Act: -0.0000

Data Index: 101230 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 4.4426. Min Range: -4.4426

Max Act: 2.9810. Min Act: -0.0000

Data Index: 1359796 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 4.4426. Min Range: -4.4426

Max Act: 2.7783. Min Act: -0.0000

Data Index: 1100357 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 4.4426. Min Range: -4.4426

Max Act: 2.5041. Min Act: -0.0000

Data Index: 1289935 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 4.4426. Min Range: -4.4426

Max Act: 2.4756. Min Act: -0.0000

Data Index: 351863 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 4.4426. Min Range: -4.4426

Max Act: 3.1196. Min Act: -0.0000

Data Index: 1194802 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 4.4426. Min Range: -4.4426

Max Act: 2.6714. Min Act: -0.0000

Data Index: 729613 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 4.4426. Min Range: -4.4426

Max Act: 2.5943. Min Act: -0.0000

Data Index: 228866 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 4.4426. Min Range: -4.4426

Max Act: 2.8019. Min Act: -0.0000

Data Index: 1131879 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 4.4426. Min Range: -4.4426

Max Act: 2.2551. Min Act: -0.0000

Data Index: 1012958 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 4.4426. Min Range: -4.4426

Max Act: 1.9179. Min Act: -0.0000

Data Index: 378172 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 4.4426. Min Range: -4.4426

Max Act: 2.2301. Min Act: -0.0000

Data Index: 338610 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 4.4426. Min Range: -4.4426

Max Act: 2.7317. Min Act: -0.0000

Data Index: 931043 (C4 (Web Text))

Max Activating Token Index: 904