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

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

Neuron 2072 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: 2.0823. Min Range: -2.0823

Max Act: 2.0823. Min Act: -0.0000

Data Index: 1593954 (Python Code)

Max Activating Token Index: 747

Text #1

Max Range: 2.0823. Min Range: -2.0823

Max Act: 1.8539. Min Act: -0.0000

Data Index: 1576885 (Python Code)

Max Activating Token Index: 251

Text #2

Max Range: 2.0823. Min Range: -2.0823

Max Act: 1.5569. Min Act: -0.0000

Data Index: 1380964 (Python Code)

Max Activating Token Index: 945

Text #3

Max Range: 2.0823. Min Range: -2.0823

Max Act: 1.2671. Min Act: -0.0000

Data Index: 1248320 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 2.0823. Min Range: -2.0823

Max Act: 1.2213. Min Act: -0.0000

Data Index: 1647167 (Python Code)

Max Activating Token Index: 273

Text #5

Max Range: 2.0823. Min Range: -2.0823

Max Act: 1.1981. Min Act: -0.0000

Data Index: 1457439 (Python Code)

Max Activating Token Index: 694

Text #6

Max Range: 2.0823. Min Range: -2.0823

Max Act: 1.2691. Min Act: -0.0000

Data Index: 1500556 (Python Code)

Max Activating Token Index: 462

Text #7

Max Range: 2.0823. Min Range: -2.0823

Max Act: 1.2142. Min Act: -0.0000

Data Index: 1562747 (Python Code)

Max Activating Token Index: 258

Text #8

Max Range: 2.0823. Min Range: -2.0823

Max Act: 1.2496. Min Act: -0.0000

Data Index: 1410210 (Python Code)

Max Activating Token Index: 506

Text #9

Max Range: 2.0823. Min Range: -2.0823

Max Act: 1.2183. Min Act: -0.0000

Data Index: 1431359 (Python Code)

Max Activating Token Index: 625

Text #10

Max Range: 2.0823. Min Range: -2.0823

Max Act: 1.4111. Min Act: -0.0000

Data Index: 1537659 (Python Code)

Max Activating Token Index: 805

Text #11

Max Range: 2.0823. Min Range: -2.0823

Max Act: 1.1204. Min Act: -0.0000

Data Index: 1486321 (Python Code)

Max Activating Token Index: 740

Text #12

Max Range: 2.0823. Min Range: -2.0823

Max Act: 1.1571. Min Act: -0.0000

Data Index: 1461369 (Python Code)

Max Activating Token Index: 672

Text #13

Max Range: 2.0823. Min Range: -2.0823

Max Act: 1.1676. Min Act: -0.0000

Data Index: 1368492 (Python Code)

Max Activating Token Index: 487

Text #14

Max Range: 2.0823. Min Range: -2.0823

Max Act: 1.2270. Min Act: -0.0000

Data Index: 1442995 (Python Code)

Max Activating Token Index: 938

Text #15

Max Range: 2.0823. Min Range: -2.0823

Max Act: 1.1431. Min Act: -0.0000

Data Index: 1415184 (Python Code)

Max Activating Token Index: 903

Text #16

Max Range: 2.0823. Min Range: -2.0823

Max Act: 1.1795. Min Act: -0.0000

Data Index: 1452092 (Python Code)

Max Activating Token Index: 274

Text #17

Max Range: 2.0823. Min Range: -2.0823

Max Act: 1.2207. Min Act: -0.0000

Data Index: 1395949 (Python Code)

Max Activating Token Index: 1007

Text #18

Max Range: 2.0823. Min Range: -2.0823

Max Act: 1.1859. Min Act: -0.0000

Data Index: 1364169 (Python Code)

Max Activating Token Index: 369

Text #19

Max Range: 2.0823. Min Range: -2.0823

Max Act: 1.1857. Min Act: -0.0000

Data Index: 1545450 (Python Code)

Max Activating Token Index: 786