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

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

Neuron 3605 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4635. Min Range: -3.4635

Max Act: 3.4635. Min Act: -0.0001

Data Index: 938486 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 3.4635. Min Range: -3.4635

Max Act: 3.3215. Min Act: -0.0001

Data Index: 825562 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 3.4635. Min Range: -3.4635

Max Act: 2.9030. Min Act: -0.0001

Data Index: 1027372 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 3.4635. Min Range: -3.4635

Max Act: 3.0478. Min Act: -0.0002

Data Index: 1258680 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 3.4635. Min Range: -3.4635

Max Act: 3.0547. Min Act: -0.0002

Data Index: 57233 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 3.4635. Min Range: -3.4635

Max Act: 3.0245. Min Act: -0.0001

Data Index: 726042 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 3.4635. Min Range: -3.4635

Max Act: 2.7432. Min Act: -0.0001

Data Index: 924992 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 3.4635. Min Range: -3.4635

Max Act: 2.8712. Min Act: -0.0001

Data Index: 848949 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 3.4635. Min Range: -3.4635

Max Act: 2.9915. Min Act: -0.0002

Data Index: 1221103 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 3.4635. Min Range: -3.4635

Max Act: 2.4765. Min Act: -0.0002

Data Index: 687721 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 3.4635. Min Range: -3.4635

Max Act: 2.7009. Min Act: -0.0001

Data Index: 179197 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 3.4635. Min Range: -3.4635

Max Act: 2.7896. Min Act: -0.0001

Data Index: 248778 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 3.4635. Min Range: -3.4635

Max Act: 2.6216. Min Act: -0.0001

Data Index: 782942 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 3.4635. Min Range: -3.4635

Max Act: 2.5092. Min Act: -0.0001

Data Index: 976200 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 3.4635. Min Range: -3.4635

Max Act: 2.4526. Min Act: -0.0001

Data Index: 1224543 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 3.4635. Min Range: -3.4635

Max Act: 2.6825. Min Act: -0.0002

Data Index: 274873 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 3.4635. Min Range: -3.4635

Max Act: 2.6851. Min Act: -0.0001

Data Index: 973432 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 3.4635. Min Range: -3.4635

Max Act: 2.5351. Min Act: -0.0001

Data Index: 1058895 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 3.4635. Min Range: -3.4635

Max Act: 2.6285. Min Act: -0.0001

Data Index: 1039265 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 3.4635. Min Range: -3.4635

Max Act: 2.7626. Min Act: -0.0002

Data Index: 562338 (C4 (Web Text))

Max Activating Token Index: 962