Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2212 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.7896. Min Act: -0.0001

Data Index: 1305743 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.8047. Min Act: -0.0001

Data Index: 1255181 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.7386. Min Act: -0.0001

Data Index: 71526 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.7609. Min Act: -0.0001

Data Index: 857201 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.7345. Min Act: -0.0000

Data Index: 513791 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.7273. Min Act: -0.0001

Data Index: 572220 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.7203. Min Act: -0.0001

Data Index: 615874 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6745. Min Act: -0.0000

Data Index: 108896 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6901. Min Act: -0.0001

Data Index: 968503 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6899. Min Act: -0.0001

Data Index: 975811 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6732. Min Act: -0.0001

Data Index: 1320097 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6647. Min Act: -0.0001

Data Index: 512788 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6670. Min Act: -0.0001

Data Index: 519891 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6421. Min Act: -0.0000

Data Index: 1225074 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6209. Min Act: -0.0001

Data Index: 948449 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6589. Min Act: -0.0001

Data Index: 792378 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6165. Min Act: -0.0001

Data Index: 954206 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1037256 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.5965. Min Act: -0.0001

Data Index: 66969 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6112. Min Act: -0.0001

Data Index: 1192709 (C4 (Web Text))

Max Activating Token Index: 321