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

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

Neuron 2550 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3365. Min Range: -2.3365

Max Act: 2.2147. Min Act: -0.0000

Data Index: 91224 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 2.3365. Min Range: -2.3365

Max Act: 2.3365. Min Act: -0.0000

Data Index: 238992 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 2.3365. Min Range: -2.3365

Max Act: 2.2635. Min Act: -0.0000

Data Index: 374619 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 2.3365. Min Range: -2.3365

Max Act: 2.1469. Min Act: -0.0000

Data Index: 719947 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 2.3365. Min Range: -2.3365

Max Act: 2.1704. Min Act: -0.0000

Data Index: 1066219 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 2.3365. Min Range: -2.3365

Max Act: 2.1658. Min Act: -0.0000

Data Index: 1113925 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 2.3365. Min Range: -2.3365

Max Act: 2.2405. Min Act: 0.0000

Data Index: 935785 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 2.3365. Min Range: -2.3365

Max Act: 2.2478. Min Act: -0.0000

Data Index: 84543 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 2.3365. Min Range: -2.3365

Max Act: 2.1112. Min Act: -0.0000

Data Index: 1178331 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 2.3365. Min Range: -2.3365

Max Act: 2.1097. Min Act: -0.0000

Data Index: 657507 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 2.3365. Min Range: -2.3365

Max Act: 1.9656. Min Act: 0.0000

Data Index: 920852 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 2.3365. Min Range: -2.3365

Max Act: 1.9609. Min Act: -0.0000

Data Index: 199075 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 2.3365. Min Range: -2.3365

Max Act: 2.0016. Min Act: -0.0000

Data Index: 185985 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 2.3365. Min Range: -2.3365

Max Act: 2.0131. Min Act: 0.0000

Data Index: 552185 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 2.3365. Min Range: -2.3365

Max Act: 2.0059. Min Act: -0.0000

Data Index: 122521 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 2.3365. Min Range: -2.3365

Max Act: 2.0690. Min Act: -0.0000

Data Index: 70942 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 2.3365. Min Range: -2.3365

Max Act: 1.8407. Min Act: 0.0000

Data Index: 377809 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 2.3365. Min Range: -2.3365

Max Act: 1.8550. Min Act: -0.0000

Data Index: 891903 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 2.3365. Min Range: -2.3365

Max Act: 2.0537. Min Act: -0.0000

Data Index: 467643 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 2.3365. Min Range: -2.3365

Max Act: 1.9570. Min Act: -0.0000

Data Index: 1229709 (C4 (Web Text))

Max Activating Token Index: 928