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

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

Neuron 3924 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1833. Min Range: -2.1833

Max Act: 2.1833. Min Act: -0.0000

Data Index: 1189980 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 2.1833. Min Range: -2.1833

Max Act: 2.0348. Min Act: -0.0000

Data Index: 146288 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 2.1833. Min Range: -2.1833

Max Act: 1.9182. Min Act: -0.0000

Data Index: 720522 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 2.1833. Min Range: -2.1833

Max Act: 2.1660. Min Act: -0.0000

Data Index: 1460725 (Python Code)

Max Activating Token Index: 951

Text #4

Max Range: 2.1833. Min Range: -2.1833

Max Act: 1.7457. Min Act: -0.0000

Data Index: 906900 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 2.1833. Min Range: -2.1833

Max Act: 1.9236. Min Act: -0.0000

Data Index: 1226891 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 2.1833. Min Range: -2.1833

Max Act: 1.6830. Min Act: -0.0000

Data Index: 855060 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 2.1833. Min Range: -2.1833

Max Act: 1.6687. Min Act: -0.0000

Data Index: 309079 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 2.1833. Min Range: -2.1833

Max Act: 1.7146. Min Act: -0.0000

Data Index: 742980 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 2.1833. Min Range: -2.1833

Max Act: 1.6057. Min Act: -0.0000

Data Index: 686939 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 2.1833. Min Range: -2.1833

Max Act: 1.6778. Min Act: -0.0000

Data Index: 1319347 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 2.1833. Min Range: -2.1833

Max Act: 1.5678. Min Act: -0.0000

Data Index: 1481573 (Python Code)

Max Activating Token Index: 308

Text #12

Max Range: 2.1833. Min Range: -2.1833

Max Act: 1.4419. Min Act: -0.0000

Data Index: 556057 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 2.1833. Min Range: -2.1833

Max Act: 1.4220. Min Act: -0.0000

Data Index: 388563 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 2.1833. Min Range: -2.1833

Max Act: 1.4840. Min Act: -0.0000

Data Index: 1087019 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 2.1833. Min Range: -2.1833

Max Act: 1.4257. Min Act: -0.0000

Data Index: 720764 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 2.1833. Min Range: -2.1833

Max Act: 1.3318. Min Act: -0.0000

Data Index: 1201957 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 2.1833. Min Range: -2.1833

Max Act: 1.2552. Min Act: -0.0000

Data Index: 833581 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 2.1833. Min Range: -2.1833

Max Act: 1.3982. Min Act: -0.0000

Data Index: 496279 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 2.1833. Min Range: -2.1833

Max Act: 1.3871. Min Act: -0.0000

Data Index: 1089681 (C4 (Web Text))

Max Activating Token Index: 924