Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1445 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.5227. Min Act: -0.0001

Data Index: 404103 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.4614. Min Act: -0.0001

Data Index: 864508 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.4386. Min Act: -0.0001

Data Index: 1014972 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3529. Min Act: -0.0001

Data Index: 295064 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3679. Min Act: -0.0001

Data Index: 81649 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3670. Min Act: -0.0001

Data Index: 928337 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3514. Min Act: -0.0001

Data Index: 890695 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3758. Min Act: -0.0001

Data Index: 652461 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3470. Min Act: -0.0001

Data Index: 479526 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3456. Min Act: -0.0001

Data Index: 713339 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3451. Min Act: -0.0001

Data Index: 663700 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3669. Min Act: -0.0001

Data Index: 139240 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3678. Min Act: -0.0001

Data Index: 208352 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3627. Min Act: -0.0001

Data Index: 375810 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3274. Min Act: -0.0001

Data Index: 736258 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3613. Min Act: -0.0001

Data Index: 1221653 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3533. Min Act: -0.0001

Data Index: 256937 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3052. Min Act: -0.0001

Data Index: 938567 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3218. Min Act: -0.0001

Data Index: 1243854 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3095. Min Act: -0.0001

Data Index: 86944 (C4 (Web Text))

Max Activating Token Index: 588