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

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

Neuron 3054 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1443. Min Range: -1.1443

Max Act: 1.1443. Min Act: -0.0000

Data Index: 1264055 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 1.1443. Min Range: -1.1443

Max Act: 1.0844. Min Act: -0.0000

Data Index: 800494 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 1.1443. Min Range: -1.1443

Max Act: 1.0662. Min Act: -0.0000

Data Index: 1055929 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.9568. Min Act: -0.0000

Data Index: 1049911 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.9270. Min Act: -0.0000

Data Index: 58191 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.9460. Min Act: -0.0000

Data Index: 1293990 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8844. Min Act: -0.0000

Data Index: 1340560 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.9112. Min Act: -0.0000

Data Index: 867955 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.9306. Min Act: -0.0000

Data Index: 654972 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.9462. Min Act: -0.0000

Data Index: 1169562 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8626. Min Act: -0.0000

Data Index: 87252 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8611. Min Act: -0.0000

Data Index: 1310583 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8651. Min Act: -0.0000

Data Index: 588642 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8498. Min Act: -0.0000

Data Index: 77308 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8800. Min Act: -0.0000

Data Index: 380625 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8420. Min Act: -0.0000

Data Index: 129096 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8234. Min Act: -0.0000

Data Index: 651399 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8589. Min Act: -0.0000

Data Index: 985166 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8556. Min Act: -0.0000

Data Index: 191294 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 1.1443. Min Range: -1.1443

Max Act: 0.8464. Min Act: -0.0000

Data Index: 461328 (C4 (Web Text))

Max Activating Token Index: 443