Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3079 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1406. Min Act: -0.0001

Data Index: 343221 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0986. Min Act: -0.0001

Data Index: 576141 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0930. Min Act: -0.0001

Data Index: 76733 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0869. Min Act: -0.0001

Data Index: 737135 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0805. Min Act: -0.0001

Data Index: 360281 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0801. Min Act: -0.0001

Data Index: 73210 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0794. Min Act: -0.0001

Data Index: 358724 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0807. Min Act: -0.0001

Data Index: 1221312 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0769. Min Act: -0.0001

Data Index: 505843 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0774. Min Act: -0.0001

Data Index: 1327369 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0736. Min Act: -0.0001

Data Index: 916467 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0768. Min Act: -0.0001

Data Index: 857462 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0756. Min Act: -0.0001

Data Index: 804588 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0729. Min Act: -0.0000

Data Index: 1195445 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1136771 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0686. Min Act: -0.0001

Data Index: 417302 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0731. Min Act: -0.0001

Data Index: 236620 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0757. Min Act: -0.0001

Data Index: 254427 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0698. Min Act: -0.0001

Data Index: 1228492 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0680. Min Act: -0.0001

Data Index: 493648 (C4 (Web Text))

Max Activating Token Index: 418