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

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

Neuron 5043 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.4329. Min Act: -0.0000

Data Index: 1076886 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.0150. Min Act: -0.0000

Data Index: 87371 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.9725. Min Act: -0.0001

Data Index: 377354 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.0084. Min Act: -0.0001

Data Index: 710886 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.8969. Min Act: -0.0000

Data Index: 245138 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.6909. Min Act: -0.0000

Data Index: 909753 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.9394. Min Act: -0.0000

Data Index: 343989 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.4089. Min Act: -0.0001

Data Index: 108345 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.7019. Min Act: -0.0001

Data Index: 1212534 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.6664. Min Act: -0.0001

Data Index: 1159958 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.4966. Min Act: -0.0001

Data Index: 602375 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.4757. Min Act: -0.0000

Data Index: 1008921 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.7426. Min Act: -0.0000

Data Index: 549767 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.5351. Min Act: -0.0001

Data Index: 418209 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.4604. Min Act: -0.0001

Data Index: 1138614 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.3192. Min Act: -0.0000

Data Index: 561366 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.4375. Min Act: -0.0000

Data Index: 1268297 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.6683. Min Act: -0.0001

Data Index: 494164 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.4173. Min Act: -0.0000

Data Index: 731676 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.5221. Min Act: -0.0001

Data Index: 1281179 (C4 (Web Text))

Max Activating Token Index: 172