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

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

Neuron 1998 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.7165. Min Act: -0.0000

Data Index: 1243863 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.6912. Min Act: -0.0000

Data Index: 882127 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.6883. Min Act: -0.0000

Data Index: 1655491 (Python Code)

Max Activating Token Index: 782

Text #3

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1173814 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.6264. Min Act: -0.0000

Data Index: 1357628 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.6599. Min Act: -0.0000

Data Index: 1487683 (Python Code)

Max Activating Token Index: 1001

Text #6

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5464. Min Act: -0.0000

Data Index: 1550147 (Python Code)

Max Activating Token Index: 711

Text #7

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5861. Min Act: 0.0000

Data Index: 1072823 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5895. Min Act: -0.0000

Data Index: 107395 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5832. Min Act: -0.0000

Data Index: 1264764 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1446001 (Python Code)

Max Activating Token Index: 621

Text #11

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.6047. Min Act: -0.0000

Data Index: 509742 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5677. Min Act: -0.0000

Data Index: 299734 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5628. Min Act: -0.0000

Data Index: 319171 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5587. Min Act: -0.0000

Data Index: 424631 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1299999 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5266. Min Act: -0.0000

Data Index: 596519 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5483. Min Act: -0.0000

Data Index: 1310640 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5316. Min Act: -0.0000

Data Index: 418242 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.7165. Min Range: -0.7165

Max Act: 0.5303. Min Act: -0.0000

Data Index: 1606101 (Python Code)

Max Activating Token Index: 745