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

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

Neuron 5648 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.9693. Min Range: -6.9693

Max Act: 6.9693. Min Act: -0.0000

Data Index: 647653 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 6.9693. Min Range: -6.9693

Max Act: 6.2046. Min Act: -0.0000

Data Index: 250028 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 6.9693. Min Range: -6.9693

Max Act: 5.4607. Min Act: -0.0000

Data Index: 84972 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 6.9693. Min Range: -6.9693

Max Act: 5.4303. Min Act: -0.0000

Data Index: 1252545 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 6.9693. Min Range: -6.9693

Max Act: 5.4086. Min Act: -0.0000

Data Index: 1056001 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 6.9693. Min Range: -6.9693

Max Act: 5.5472. Min Act: -0.0000

Data Index: 547541 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 6.9693. Min Range: -6.9693

Max Act: 5.3085. Min Act: -0.0000

Data Index: 612749 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 6.9693. Min Range: -6.9693

Max Act: 5.5311. Min Act: -0.0000

Data Index: 121339 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 6.9693. Min Range: -6.9693

Max Act: 5.7260. Min Act: -0.0000

Data Index: 606006 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 6.9693. Min Range: -6.9693

Max Act: 5.4435. Min Act: -0.0000

Data Index: 692609 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 6.9693. Min Range: -6.9693

Max Act: 5.4366. Min Act: -0.0000

Data Index: 371081 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 6.9693. Min Range: -6.9693

Max Act: 5.0845. Min Act: -0.0000

Data Index: 490973 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 6.9693. Min Range: -6.9693

Max Act: 5.0565. Min Act: -0.0000

Data Index: 209695 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 6.9693. Min Range: -6.9693

Max Act: 5.1172. Min Act: -0.0000

Data Index: 664779 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 6.9693. Min Range: -6.9693

Max Act: 5.0588. Min Act: -0.0000

Data Index: 345848 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 6.9693. Min Range: -6.9693

Max Act: 4.8128. Min Act: -0.0000

Data Index: 383507 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 6.9693. Min Range: -6.9693

Max Act: 4.8230. Min Act: -0.0000

Data Index: 1089623 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 6.9693. Min Range: -6.9693

Max Act: 4.8412. Min Act: -0.0000

Data Index: 1048350 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 6.9693. Min Range: -6.9693

Max Act: 4.3424. Min Act: -0.0000

Data Index: 1357855 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 6.9693. Min Range: -6.9693

Max Act: 4.9224. Min Act: -0.0000

Data Index: 109475 (C4 (Web Text))

Max Activating Token Index: 48