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

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

Neuron 555 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: 6.7201. Min Range: -6.7201

Max Act: 6.7201. Min Act: -0.0000

Data Index: 852537 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 6.7201. Min Range: -6.7201

Max Act: 6.0919. Min Act: -0.0000

Data Index: 1016452 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 6.7201. Min Range: -6.7201

Max Act: 5.3972. Min Act: -0.0000

Data Index: 191289 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 6.7201. Min Range: -6.7201

Max Act: 5.4363. Min Act: -0.0000

Data Index: 1285621 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 6.7201. Min Range: -6.7201

Max Act: 5.1001. Min Act: -0.0000

Data Index: 1294066 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 6.7201. Min Range: -6.7201

Max Act: 5.2332. Min Act: -0.0000

Data Index: 836525 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 6.7201. Min Range: -6.7201

Max Act: 5.2444. Min Act: -0.0000

Data Index: 1224971 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 6.7201. Min Range: -6.7201

Max Act: 5.0056. Min Act: -0.0000

Data Index: 1286639 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 6.7201. Min Range: -6.7201

Max Act: 5.5808. Min Act: -0.0000

Data Index: 392081 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 6.7201. Min Range: -6.7201

Max Act: 4.6669. Min Act: -0.0000

Data Index: 385831 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 6.7201. Min Range: -6.7201

Max Act: 4.6325. Min Act: -0.0000

Data Index: 1041537 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 6.7201. Min Range: -6.7201

Max Act: 4.3966. Min Act: -0.0000

Data Index: 120561 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 6.7201. Min Range: -6.7201

Max Act: 4.9492. Min Act: -0.0000

Data Index: 1178555 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 6.7201. Min Range: -6.7201

Max Act: 4.5775. Min Act: -0.0000

Data Index: 451203 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 6.7201. Min Range: -6.7201

Max Act: 4.6912. Min Act: -0.0000

Data Index: 1212015 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 6.7201. Min Range: -6.7201

Max Act: 4.6094. Min Act: -0.0000

Data Index: 913490 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 6.7201. Min Range: -6.7201

Max Act: 4.5194. Min Act: -0.0000

Data Index: 926620 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 6.7201. Min Range: -6.7201

Max Act: 4.5326. Min Act: -0.0000

Data Index: 987437 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 6.7201. Min Range: -6.7201

Max Act: 4.6886. Min Act: -0.0000

Data Index: 845452 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 6.7201. Min Range: -6.7201

Max Act: 4.3135. Min Act: -0.0000

Data Index: 1048548 (C4 (Web Text))

Max Activating Token Index: 22