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

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

Neuron 3634 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.2395. Min Act: -0.0001

Data Index: 891084 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0619. Min Act: -0.0001

Data Index: 1165351 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.1094. Min Act: -0.0001

Data Index: 152449 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0795. Min Act: -0.0001

Data Index: 523108 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0164. Min Act: -0.0001

Data Index: 6850 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0103. Min Act: -0.0001

Data Index: 820368 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0477. Min Act: -0.0001

Data Index: 1295986 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0674. Min Act: -0.0001

Data Index: 241547 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9551. Min Act: -0.0001

Data Index: 604446 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0497. Min Act: -0.0001

Data Index: 14554 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9400. Min Act: -0.0001

Data Index: 1326659 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9667. Min Act: -0.0001

Data Index: 521073 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9710. Min Act: -0.0001

Data Index: 6734 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8825. Min Act: -0.0001

Data Index: 767020 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9856. Min Act: -0.0001

Data Index: 1245855 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9559. Min Act: -0.0001

Data Index: 288794 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9487. Min Act: -0.0001

Data Index: 967803 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9463. Min Act: -0.0001

Data Index: 865547 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9107. Min Act: -0.0001

Data Index: 250039 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9132. Min Act: -0.0001

Data Index: 1352982 (C4 (Web Text))

Max Activating Token Index: 6