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

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

Neuron 1569 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1986. Min Range: -3.1986

Max Act: 3.1986. Min Act: -0.0000

Data Index: 482925 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 3.1986. Min Range: -3.1986

Max Act: 2.5088. Min Act: -0.0000

Data Index: 941627 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 3.1986. Min Range: -3.1986

Max Act: 2.2550. Min Act: -0.0000

Data Index: 35702 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 3.1986. Min Range: -3.1986

Max Act: 1.7922. Min Act: -0.0000

Data Index: 1130356 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 3.1986. Min Range: -3.1986

Max Act: 1.9811. Min Act: -0.0000

Data Index: 189850 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 3.1986. Min Range: -3.1986

Max Act: 2.1208. Min Act: -0.0000

Data Index: 750393 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 3.1986. Min Range: -3.1986

Max Act: 1.8311. Min Act: -0.0000

Data Index: 1268657 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 3.1986. Min Range: -3.1986

Max Act: 2.0492. Min Act: -0.0000

Data Index: 323878 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 3.1986. Min Range: -3.1986

Max Act: 1.9385. Min Act: -0.0000

Data Index: 742924 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 3.1986. Min Range: -3.1986

Max Act: 1.9860. Min Act: -0.0000

Data Index: 1158472 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 3.1986. Min Range: -3.1986

Max Act: 1.8949. Min Act: -0.0000

Data Index: 143565 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 3.1986. Min Range: -3.1986

Max Act: 1.9381. Min Act: -0.0000

Data Index: 172215 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 3.1986. Min Range: -3.1986

Max Act: 1.9103. Min Act: -0.0000

Data Index: 342175 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 3.1986. Min Range: -3.1986

Max Act: 1.6725. Min Act: -0.0000

Data Index: 614452 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 3.1986. Min Range: -3.1986

Max Act: 2.0492. Min Act: -0.0000

Data Index: 453490 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 3.1986. Min Range: -3.1986

Max Act: 1.5240. Min Act: -0.0000

Data Index: 573592 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 3.1986. Min Range: -3.1986

Max Act: 1.7882. Min Act: -0.0000

Data Index: 521397 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 3.1986. Min Range: -3.1986

Max Act: 1.6730. Min Act: -0.0000

Data Index: 353747 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 3.1986. Min Range: -3.1986

Max Act: 1.7435. Min Act: -0.0000

Data Index: 190361 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 3.1986. Min Range: -3.1986

Max Act: 1.6466. Min Act: -0.0000

Data Index: 759351 (C4 (Web Text))

Max Activating Token Index: 759