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

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

Neuron 2170 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: 0.6734. Min Range: -0.6734

Max Act: 0.6428. Min Act: -0.0000

Data Index: 853258 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.6734. Min Act: -0.0000

Data Index: 883597 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1300448 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1316097 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.5671. Min Act: -0.0000

Data Index: 691631 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.5586. Min Act: -0.0000

Data Index: 1334684 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.5544. Min Act: -0.0000

Data Index: 319235 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.5488. Min Act: -0.0000

Data Index: 261312 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.5596. Min Act: -0.0000

Data Index: 1240629 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.5195. Min Act: -0.0000

Data Index: 822935 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.5141. Min Act: 0.0000

Data Index: 155378 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4978. Min Act: -0.0000

Data Index: 181858 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4684. Min Act: -0.0000

Data Index: 391122 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4562. Min Act: -0.0000

Data Index: 661356 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4248. Min Act: -0.0000

Data Index: 1286560 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4659. Min Act: -0.0000

Data Index: 702379 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4480. Min Act: -0.0000

Data Index: 604465 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1255762 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4702. Min Act: -0.0000

Data Index: 1055380 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4239. Min Act: -0.0000

Data Index: 536865 (C4 (Web Text))

Max Activating Token Index: 843