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

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

Neuron 3183 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2986. Min Range: -2.2986

Max Act: 2.0765. Min Act: -0.0001

Data Index: 890612 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 2.2986. Min Range: -2.2986

Max Act: 2.1873. Min Act: -0.0001

Data Index: 578566 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 2.2986. Min Range: -2.2986

Max Act: 2.2986. Min Act: -0.0001

Data Index: 1051929 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.6611. Min Act: -0.0001

Data Index: 727189 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.8498. Min Act: -0.0001

Data Index: 1234516 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.6302. Min Act: -0.0001

Data Index: 1137345 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.5592. Min Act: -0.0001

Data Index: 1282903 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.8054. Min Act: -0.0001

Data Index: 323999 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.5851. Min Act: -0.0001

Data Index: 1214421 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.4055. Min Act: -0.0001

Data Index: 970408 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.4164. Min Act: -0.0001

Data Index: 544129 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.4211. Min Act: -0.0001

Data Index: 1119736 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.4479. Min Act: -0.0001

Data Index: 1188221 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.3303. Min Act: -0.0001

Data Index: 862984 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.5333. Min Act: -0.0001

Data Index: 167194 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.4705. Min Act: -0.0001

Data Index: 822627 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.4286. Min Act: -0.0001

Data Index: 841357 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.3371. Min Act: -0.0001

Data Index: 863719 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.2228. Min Act: -0.0001

Data Index: 1003089 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 2.2986. Min Range: -2.2986

Max Act: 1.5402. Min Act: -0.0001

Data Index: 1260635 (C4 (Web Text))

Max Activating Token Index: 546