Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2326 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.4672. Min Act: -0.0000

Data Index: 298272 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3744. Min Act: -0.0000

Data Index: 663630 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1230070 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1246646 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3570. Min Act: -0.0000

Data Index: 630016 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3816. Min Act: -0.0000

Data Index: 910362 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3822. Min Act: -0.0000

Data Index: 485960 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3662. Min Act: -0.0000

Data Index: 689973 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3783. Min Act: -0.0000

Data Index: 211055 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3747. Min Act: -0.0000

Data Index: 515186 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3602. Min Act: -0.0000

Data Index: 952310 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3586. Min Act: -0.0000

Data Index: 938457 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3463. Min Act: -0.0000

Data Index: 242470 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1310569 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3439. Min Act: -0.0000

Data Index: 924710 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3527. Min Act: -0.0000

Data Index: 911937 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3372. Min Act: -0.0000

Data Index: 781299 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3474. Min Act: 0.0000

Data Index: 245677 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3318. Min Act: -0.0000

Data Index: 24124 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3320. Min Act: -0.0000

Data Index: 673855 (C4 (Web Text))

Max Activating Token Index: 842