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

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

Neuron 1859 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5924. Min Act: -0.0000

Data Index: 283997 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5623. Min Act: -0.0000

Data Index: 1170684 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5986. Min Act: -0.0000

Data Index: 594612 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5733. Min Act: -0.0000

Data Index: 804128 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5902. Min Act: -0.0000

Data Index: 428068 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5541. Min Act: -0.0000

Data Index: 145523 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5679. Min Act: -0.0000

Data Index: 430800 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5323. Min Act: -0.0000

Data Index: 968234 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5633. Min Act: -0.0000

Data Index: 26523 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5388. Min Act: -0.0000

Data Index: 798660 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5554. Min Act: -0.0000

Data Index: 224131 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5443. Min Act: -0.0000

Data Index: 401713 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1175706 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5226. Min Act: -0.0000

Data Index: 771194 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5019. Min Act: -0.0000

Data Index: 1044027 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5352. Min Act: -0.0000

Data Index: 128727 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5126. Min Act: -0.0000

Data Index: 1292060 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5118. Min Act: -0.0000

Data Index: 912198 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1313305 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5150. Min Act: -0.0000

Data Index: 626256 (C4 (Web Text))

Max Activating Token Index: 952