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

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

Neuron 5759 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1139. Min Range: -2.1139

Max Act: 2.1139. Min Act: -0.0000

Data Index: 292982 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 2.1139. Min Range: -2.1139

Max Act: 1.5998. Min Act: -0.0000

Data Index: 262951 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 2.1139. Min Range: -2.1139

Max Act: 1.4236. Min Act: -0.0000

Data Index: 1329032 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 2.1139. Min Range: -2.1139

Max Act: 1.4064. Min Act: -0.0000

Data Index: 170433 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 2.1139. Min Range: -2.1139

Max Act: 1.3128. Min Act: -0.0000

Data Index: 893780 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 2.1139. Min Range: -2.1139

Max Act: 1.2531. Min Act: -0.0000

Data Index: 1000793 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 2.1139. Min Range: -2.1139

Max Act: 1.3034. Min Act: -0.0000

Data Index: 862933 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 2.1139. Min Range: -2.1139

Max Act: 1.1303. Min Act: -0.0000

Data Index: 1019712 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 2.1139. Min Range: -2.1139

Max Act: 1.1531. Min Act: 0.0000

Data Index: 416605 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 2.1139. Min Range: -2.1139

Max Act: 1.1340. Min Act: 0.0000

Data Index: 491820 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 2.1139. Min Range: -2.1139

Max Act: 1.1289. Min Act: 0.0000

Data Index: 222761 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 2.1139. Min Range: -2.1139

Max Act: 1.1248. Min Act: -0.0000

Data Index: 984380 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 2.1139. Min Range: -2.1139

Max Act: 1.0934. Min Act: 0.0000

Data Index: 620460 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 2.1139. Min Range: -2.1139

Max Act: 1.0929. Min Act: -0.0000

Data Index: 849874 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 2.1139. Min Range: -2.1139

Max Act: 1.0931. Min Act: -0.0000

Data Index: 315107 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 2.1139. Min Range: -2.1139

Max Act: 0.9750. Min Act: -0.0000

Data Index: 713106 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 2.1139. Min Range: -2.1139

Max Act: 1.0383. Min Act: 0.0000

Data Index: 1005967 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 2.1139. Min Range: -2.1139

Max Act: 1.0334. Min Act: -0.0000

Data Index: 1055324 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 2.1139. Min Range: -2.1139

Max Act: 1.0615. Min Act: -0.0000

Data Index: 69045 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 2.1139. Min Range: -2.1139

Max Act: 1.0347. Min Act: -0.0000

Data Index: 788239 (C4 (Web Text))

Max Activating Token Index: 472