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

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

Neuron 3061 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5431. Min Range: -3.5431

Max Act: 3.5431. Min Act: -0.0001

Data Index: 1040534 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 3.5431. Min Range: -3.5431

Max Act: 3.2110. Min Act: -0.0001

Data Index: 380098 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 3.5431. Min Range: -3.5431

Max Act: 3.2816. Min Act: -0.0001

Data Index: 504633 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 3.5431. Min Range: -3.5431

Max Act: 2.9742. Min Act: -0.0001

Data Index: 1094545 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 3.5431. Min Range: -3.5431

Max Act: 2.7229. Min Act: -0.0000

Data Index: 578283 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 3.5431. Min Range: -3.5431

Max Act: 2.8210. Min Act: -0.0001

Data Index: 60937 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 3.5431. Min Range: -3.5431

Max Act: 2.8514. Min Act: -0.0001

Data Index: 645272 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 3.5431. Min Range: -3.5431

Max Act: 2.4807. Min Act: -0.0001

Data Index: 1157336 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 3.5431. Min Range: -3.5431

Max Act: 2.3121. Min Act: -0.0001

Data Index: 1166618 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 3.5431. Min Range: -3.5431

Max Act: 2.2778. Min Act: -0.0001

Data Index: 529618 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 3.5431. Min Range: -3.5431

Max Act: 2.3422. Min Act: -0.0001

Data Index: 183393 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 3.5431. Min Range: -3.5431

Max Act: 2.1567. Min Act: -0.0001

Data Index: 889768 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 3.5431. Min Range: -3.5431

Max Act: 2.2490. Min Act: -0.0001

Data Index: 802347 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 3.5431. Min Range: -3.5431

Max Act: 2.2414. Min Act: -0.0001

Data Index: 279981 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 3.5431. Min Range: -3.5431

Max Act: 2.2225. Min Act: -0.0001

Data Index: 967295 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 3.5431. Min Range: -3.5431

Max Act: 2.1965. Min Act: -0.0000

Data Index: 1355300 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 3.5431. Min Range: -3.5431

Max Act: 2.1877. Min Act: -0.0001

Data Index: 646911 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 3.5431. Min Range: -3.5431

Max Act: 2.1724. Min Act: -0.0000

Data Index: 29067 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 3.5431. Min Range: -3.5431

Max Act: 2.0636. Min Act: -0.0001

Data Index: 70913 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 3.5431. Min Range: -3.5431

Max Act: 2.0642. Min Act: -0.0001

Data Index: 379795 (C4 (Web Text))

Max Activating Token Index: 344