Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4543 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4500. Min Range: -2.4500

Max Act: 2.4500. Min Act: -0.0000

Data Index: 180262 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 2.4500. Min Range: -2.4500

Max Act: 2.3785. Min Act: -0.0000

Data Index: 1096650 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 2.4500. Min Range: -2.4500

Max Act: 2.3534. Min Act: -0.0000

Data Index: 981021 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 2.4500. Min Range: -2.4500

Max Act: 2.2111. Min Act: -0.0000

Data Index: 1237174 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 2.4500. Min Range: -2.4500

Max Act: 2.1911. Min Act: -0.0000

Data Index: 1355808 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 2.4500. Min Range: -2.4500

Max Act: 2.1705. Min Act: 0.0000

Data Index: 330803 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 2.4500. Min Range: -2.4500

Max Act: 2.0962. Min Act: -0.0000

Data Index: 1229227 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 2.4500. Min Range: -2.4500

Max Act: 2.1453. Min Act: -0.0000

Data Index: 1178880 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 2.4500. Min Range: -2.4500

Max Act: 2.0336. Min Act: 0.0000

Data Index: 54791 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 2.4500. Min Range: -2.4500

Max Act: 1.9463. Min Act: -0.0000

Data Index: 1219131 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 2.4500. Min Range: -2.4500

Max Act: 1.9516. Min Act: -0.0000

Data Index: 504718 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 2.4500. Min Range: -2.4500

Max Act: 1.9041. Min Act: -0.0000

Data Index: 1030434 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 2.4500. Min Range: -2.4500

Max Act: 1.9033. Min Act: -0.0000

Data Index: 174615 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 2.4500. Min Range: -2.4500

Max Act: 1.9154. Min Act: -0.0000

Data Index: 1315084 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 2.4500. Min Range: -2.4500

Max Act: 1.9039. Min Act: -0.0000

Data Index: 113132 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 2.4500. Min Range: -2.4500

Max Act: 1.7956. Min Act: -0.0000

Data Index: 1103049 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 2.4500. Min Range: -2.4500

Max Act: 1.9636. Min Act: -0.0000

Data Index: 612400 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 2.4500. Min Range: -2.4500

Max Act: 1.6965. Min Act: -0.0000

Data Index: 334158 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 2.4500. Min Range: -2.4500

Max Act: 1.7825. Min Act: -0.0000

Data Index: 880594 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 2.4500. Min Range: -2.4500

Max Act: 1.7746. Min Act: -0.0000

Data Index: 815931 (C4 (Web Text))

Max Activating Token Index: 765