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

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

Neuron 3706 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6112. Min Range: -1.6112

Max Act: 1.5718. Min Act: -0.0000

Data Index: 1274027 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 1.6112. Min Range: -1.6112

Max Act: 1.6112. Min Act: -0.0000

Data Index: 569140 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 1.6112. Min Range: -1.6112

Max Act: 1.2849. Min Act: -0.0000

Data Index: 740924 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 1.6112. Min Range: -1.6112

Max Act: 1.3370. Min Act: -0.0000

Data Index: 939393 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 1.6112. Min Range: -1.6112

Max Act: 1.2490. Min Act: -0.0000

Data Index: 1305499 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 1.6112. Min Range: -1.6112

Max Act: 1.1738. Min Act: -0.0000

Data Index: 1345271 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 1.6112. Min Range: -1.6112

Max Act: 1.2307. Min Act: -0.0000

Data Index: 935467 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 1.6112. Min Range: -1.6112

Max Act: 1.2734. Min Act: -0.0000

Data Index: 245495 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 1.6112. Min Range: -1.6112

Max Act: 1.1061. Min Act: -0.0000

Data Index: 237761 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 1.6112. Min Range: -1.6112

Max Act: 1.2408. Min Act: -0.0000

Data Index: 800262 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 1.6112. Min Range: -1.6112

Max Act: 1.0724. Min Act: -0.0000

Data Index: 22855 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 1.6112. Min Range: -1.6112

Max Act: 1.1341. Min Act: -0.0000

Data Index: 868215 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 1.6112. Min Range: -1.6112

Max Act: 1.1220. Min Act: -0.0000

Data Index: 766624 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 1.6112. Min Range: -1.6112

Max Act: 1.0847. Min Act: -0.0000

Data Index: 1463628 (Python Code)

Max Activating Token Index: 614

Text #14

Max Range: 1.6112. Min Range: -1.6112

Max Act: 1.1140. Min Act: -0.0000

Data Index: 124979 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 1.6112. Min Range: -1.6112

Max Act: 1.1020. Min Act: -0.0000

Data Index: 1174379 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 1.6112. Min Range: -1.6112

Max Act: 1.1005. Min Act: -0.0000

Data Index: 234051 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 1.6112. Min Range: -1.6112

Max Act: 1.0933. Min Act: -0.0000

Data Index: 1185391 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 1.6112. Min Range: -1.6112

Max Act: 1.0920. Min Act: -0.0000

Data Index: 61216 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 1.6112. Min Range: -1.6112

Max Act: 1.0550. Min Act: -0.0000

Data Index: 1305269 (C4 (Web Text))

Max Activating Token Index: 70