Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4648 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.7273. Min Act: -0.0000

Data Index: 580089 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6944. Min Act: -0.0000

Data Index: 680878 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1167614 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6604. Min Act: -0.0000

Data Index: 1250887 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6343. Min Act: -0.0000

Data Index: 1052927 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6475. Min Act: -0.0000

Data Index: 613310 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6232. Min Act: -0.0000

Data Index: 910950 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1334882 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6234. Min Act: -0.0000

Data Index: 157246 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5778. Min Act: -0.0000

Data Index: 1299022 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5974. Min Act: -0.0000

Data Index: 1237892 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5563. Min Act: -0.0000

Data Index: 152536 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5787. Min Act: -0.0000

Data Index: 27129 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5378. Min Act: -0.0000

Data Index: 510942 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5843. Min Act: -0.0000

Data Index: 170669 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5650. Min Act: -0.0000

Data Index: 534133 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5838. Min Act: -0.0000

Data Index: 314737 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1144430 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5903. Min Act: -0.0000

Data Index: 295394 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5492. Min Act: -0.0000

Data Index: 909336 (C4 (Web Text))

Max Activating Token Index: 528