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

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

Neuron 3218 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.4002. Min Act: -0.0000

Data Index: 405489 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3563. Min Act: 0.0001

Data Index: 795326 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3451. Min Act: -0.0000

Data Index: 697616 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3365. Min Act: -0.0000

Data Index: 736287 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3552. Min Act: -0.0000

Data Index: 815487 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3432. Min Act: -0.0000

Data Index: 345606 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3370. Min Act: -0.0000

Data Index: 738229 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3323. Min Act: -0.0000

Data Index: 104562 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3461. Min Act: -0.0000

Data Index: 509309 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3324. Min Act: -0.0000

Data Index: 1274978 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3316. Min Act: -0.0000

Data Index: 58732 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3313. Min Act: -0.0000

Data Index: 1187027 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3227. Min Act: -0.0000

Data Index: 753850 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3117. Min Act: -0.0000

Data Index: 390580 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3064. Min Act: -0.0000

Data Index: 937149 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3149. Min Act: -0.0000

Data Index: 560413 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2963. Min Act: -0.0000

Data Index: 944038 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2984. Min Act: -0.0000

Data Index: 395980 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3107. Min Act: -0.0000

Data Index: 183349 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.2816. Min Act: -0.0000

Data Index: 1132616 (C4 (Web Text))

Max Activating Token Index: 493