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

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

Neuron 4749 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6636. Min Act: -0.0000

Data Index: 570832 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1279043 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5385. Min Act: -0.0000

Data Index: 569704 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5205. Min Act: -0.0000

Data Index: 63651 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.3860. Min Act: -0.0000

Data Index: 29154 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4518. Min Act: -0.0000

Data Index: 101407 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4555. Min Act: -0.0000

Data Index: 987260 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4658. Min Act: -0.0000

Data Index: 322081 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4831. Min Act: -0.0000

Data Index: 148876 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4644. Min Act: -0.0000

Data Index: 920722 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1228924 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4114. Min Act: -0.0000

Data Index: 1539531 (Python Code)

Max Activating Token Index: 222

Text #12

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4748. Min Act: -0.0000

Data Index: 821768 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4558. Min Act: -0.0000

Data Index: 745122 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.3640. Min Act: -0.0000

Data Index: 798927 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1184539 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4136. Min Act: -0.0000

Data Index: 657442 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4250. Min Act: -0.0000

Data Index: 230132 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4278. Min Act: -0.0000

Data Index: 1226939 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4065. Min Act: -0.0000

Data Index: 534551 (C4 (Web Text))

Max Activating Token Index: 721