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

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

Neuron 666 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: 2.4609. Min Range: -2.4609

Max Act: 2.4609. Min Act: -0.0000

Data Index: 597942 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.2375. Min Act: -0.0000

Data Index: 1167835 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.1952. Min Act: -0.0000

Data Index: 1025566 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.1737. Min Act: -0.0000

Data Index: 298704 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.1413. Min Act: -0.0000

Data Index: 1084419 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.0859. Min Act: -0.0000

Data Index: 329666 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.0974. Min Act: -0.0000

Data Index: 337788 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.0661. Min Act: -0.0000

Data Index: 69975 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.0522. Min Act: -0.0000

Data Index: 598462 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.0575. Min Act: -0.0000

Data Index: 686186 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.0448. Min Act: -0.0000

Data Index: 815575 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.1637. Min Act: -0.0000

Data Index: 1000343 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.0242. Min Act: -0.0000

Data Index: 598576 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.0101. Min Act: -0.0000

Data Index: 546131 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.0133. Min Act: -0.0000

Data Index: 1054569 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.0196. Min Act: -0.0000

Data Index: 1195577 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 2.4609. Min Range: -2.4609

Max Act: 1.9966. Min Act: -0.0000

Data Index: 889791 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.0056. Min Act: -0.0000

Data Index: 381040 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 2.4609. Min Range: -2.4609

Max Act: 1.9875. Min Act: -0.0000

Data Index: 1000408 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 2.4609. Min Range: -2.4609

Max Act: 1.9924. Min Act: -0.0000

Data Index: 1257753 (C4 (Web Text))

Max Activating Token Index: 570