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

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

Neuron 4459 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.4542. Min Act: -0.0002

Data Index: 777630 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.2704. Min Act: -0.0002

Data Index: 101062 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.2278. Min Act: -0.0002

Data Index: 718140 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.2440. Min Act: -0.0002

Data Index: 679852 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.0341. Min Act: -0.0002

Data Index: 97144 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.2215. Min Act: -0.0002

Data Index: 1332997 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1847. Min Act: -0.0002

Data Index: 5215 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1071. Min Act: -0.0002

Data Index: 956230 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1175. Min Act: -0.0002

Data Index: 854296 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.0985. Min Act: -0.0002

Data Index: 490324 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1249. Min Act: -0.0002

Data Index: 963590 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.2131. Min Act: -0.0002

Data Index: 939888 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1790. Min Act: -0.0002

Data Index: 538891 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.2008. Min Act: -0.0002

Data Index: 994227 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.0352. Min Act: -0.0002

Data Index: 1259845 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1258. Min Act: -0.0002

Data Index: 1384 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.0816. Min Act: -0.0002

Data Index: 1059380 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1454. Min Act: -0.0002

Data Index: 1340294 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.0548. Min Act: -0.0002

Data Index: 254288 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1284. Min Act: -0.0002

Data Index: 615873 (C4 (Web Text))

Max Activating Token Index: 902