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

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

Neuron 1169 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0509. Min Range: -6.0509

Max Act: 6.0509. Min Act: -0.0000

Data Index: 241985 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 6.0509. Min Range: -6.0509

Max Act: 3.8898. Min Act: -0.0000

Data Index: 1090710 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 6.0509. Min Range: -6.0509

Max Act: 3.9431. Min Act: -0.0000

Data Index: 686395 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 6.0509. Min Range: -6.0509

Max Act: 3.5847. Min Act: -0.0000

Data Index: 679004 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 6.0509. Min Range: -6.0509

Max Act: 3.4585. Min Act: -0.0000

Data Index: 1091563 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 6.0509. Min Range: -6.0509

Max Act: 3.2103. Min Act: 0.0000

Data Index: 217637 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 6.0509. Min Range: -6.0509

Max Act: 2.8620. Min Act: -0.0000

Data Index: 746399 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 6.0509. Min Range: -6.0509

Max Act: 3.2509. Min Act: -0.0000

Data Index: 1213360 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 6.0509. Min Range: -6.0509

Max Act: 3.1724. Min Act: -0.0000

Data Index: 1315465 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 6.0509. Min Range: -6.0509

Max Act: 3.1475. Min Act: -0.0000

Data Index: 1301411 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 6.0509. Min Range: -6.0509

Max Act: 3.0615. Min Act: -0.0000

Data Index: 55893 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 6.0509. Min Range: -6.0509

Max Act: 3.1997. Min Act: -0.0000

Data Index: 758706 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 6.0509. Min Range: -6.0509

Max Act: 3.0523. Min Act: -0.0000

Data Index: 1112434 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 6.0509. Min Range: -6.0509

Max Act: 3.0061. Min Act: -0.0000

Data Index: 126390 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 6.0509. Min Range: -6.0509

Max Act: 2.8303. Min Act: -0.0000

Data Index: 1166761 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 6.0509. Min Range: -6.0509

Max Act: 2.8300. Min Act: -0.0000

Data Index: 130251 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 6.0509. Min Range: -6.0509

Max Act: 2.7899. Min Act: -0.0000

Data Index: 1056734 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 6.0509. Min Range: -6.0509

Max Act: 2.7760. Min Act: -0.0000

Data Index: 631260 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 6.0509. Min Range: -6.0509

Max Act: 2.8630. Min Act: 0.0000

Data Index: 1287362 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 6.0509. Min Range: -6.0509

Max Act: 2.8304. Min Act: -0.0000

Data Index: 228451 (C4 (Web Text))

Max Activating Token Index: 930