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

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

Neuron 5756 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: 2.3538. Min Range: -2.3538

Max Act: 2.3538. Min Act: -0.0000

Data Index: 37292 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 2.3538. Min Range: -2.3538

Max Act: 2.2774. Min Act: -0.0000

Data Index: 262358 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 2.3538. Min Range: -2.3538

Max Act: 2.0865. Min Act: -0.0000

Data Index: 1355276 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 2.3538. Min Range: -2.3538

Max Act: 2.1345. Min Act: -0.0000

Data Index: 143326 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 2.3538. Min Range: -2.3538

Max Act: 2.0306. Min Act: -0.0000

Data Index: 764569 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 2.3538. Min Range: -2.3538

Max Act: 2.0545. Min Act: -0.0000

Data Index: 1158511 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 2.3538. Min Range: -2.3538

Max Act: 2.0509. Min Act: -0.0000

Data Index: 698756 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.9459. Min Act: -0.0000

Data Index: 531062 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.9820. Min Act: -0.0000

Data Index: 566303 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.9687. Min Act: -0.0000

Data Index: 1162206 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.9894. Min Act: -0.0000

Data Index: 686806 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.9740. Min Act: -0.0000

Data Index: 449178 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.8422. Min Act: -0.0000

Data Index: 614752 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.9553. Min Act: -0.0000

Data Index: 319949 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 2.3538. Min Range: -2.3538

Max Act: 2.0658. Min Act: -0.0000

Data Index: 907101 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.9622. Min Act: -0.0000

Data Index: 564798 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 2.3538. Min Range: -2.3538

Max Act: 2.0294. Min Act: -0.0000

Data Index: 144784 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 2.3538. Min Range: -2.3538

Max Act: 2.0566. Min Act: -0.0000

Data Index: 557269 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.9357. Min Act: -0.0000

Data Index: 1273044 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 2.3538. Min Range: -2.3538

Max Act: 1.9388. Min Act: -0.0000

Data Index: 593067 (C4 (Web Text))

Max Activating Token Index: 968