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

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

Neuron 6129 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.2401. Min Act: -0.0001

Data Index: 1248557 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.2315. Min Act: -0.0000

Data Index: 1171838 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.2158. Min Act: -0.0000

Data Index: 62964 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.2163. Min Act: -0.0001

Data Index: 1128711 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1073871 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.2295. Min Act: -0.0001

Data Index: 1209064 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1868. Min Act: -0.0000

Data Index: 10708 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.2115. Min Act: -0.0000

Data Index: 1561295 (Python Code)

Max Activating Token Index: 220

Text #8

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1771. Min Act: -0.0000

Data Index: 269068 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1813. Min Act: -0.0000

Data Index: 494043 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.2006. Min Act: -0.0000

Data Index: 962564 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1074908 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1762. Min Act: -0.0000

Data Index: 573119 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1859. Min Act: -0.0001

Data Index: 1335411 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1910. Min Act: -0.0000

Data Index: 167192 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1650. Min Act: -0.0001

Data Index: 271392 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1755. Min Act: -0.0000

Data Index: 1334369 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1609. Min Act: -0.0000

Data Index: 749930 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1709. Min Act: -0.0000

Data Index: 805288 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1661. Min Act: -0.0000

Data Index: 541872 (C4 (Web Text))

Max Activating Token Index: 215