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

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

Neuron 3645 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: 2.1973. Min Range: -2.1973

Max Act: 2.1973. Min Act: -0.0000

Data Index: 968796 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 2.1973. Min Range: -2.1973

Max Act: 1.9709. Min Act: -0.0000

Data Index: 311946 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 2.1973. Min Range: -2.1973

Max Act: 1.9518. Min Act: -0.0000

Data Index: 686006 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 2.1973. Min Range: -2.1973

Max Act: 1.8513. Min Act: -0.0000

Data Index: 792189 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 2.1973. Min Range: -2.1973

Max Act: 1.3343. Min Act: -0.0000

Data Index: 270123 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 2.1973. Min Range: -2.1973

Max Act: 1.4476. Min Act: -0.0000

Data Index: 41539 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 2.1973. Min Range: -2.1973

Max Act: 1.4228. Min Act: -0.0000

Data Index: 710565 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 2.1973. Min Range: -2.1973

Max Act: 1.4152. Min Act: -0.0000

Data Index: 464906 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 2.1973. Min Range: -2.1973

Max Act: 1.3770. Min Act: -0.0000

Data Index: 790301 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 2.1973. Min Range: -2.1973

Max Act: 1.2750. Min Act: -0.0000

Data Index: 1323024 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 2.1973. Min Range: -2.1973

Max Act: 1.2911. Min Act: -0.0000

Data Index: 1213862 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 2.1973. Min Range: -2.1973

Max Act: 1.1404. Min Act: -0.0000

Data Index: 149941 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 2.1973. Min Range: -2.1973

Max Act: 1.0468. Min Act: -0.0000

Data Index: 701846 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 2.1973. Min Range: -2.1973

Max Act: 1.1637. Min Act: -0.0000

Data Index: 176080 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 2.1973. Min Range: -2.1973

Max Act: 1.2228. Min Act: -0.0000

Data Index: 1045117 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 2.1973. Min Range: -2.1973

Max Act: 1.1372. Min Act: -0.0000

Data Index: 46553 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 2.1973. Min Range: -2.1973

Max Act: 1.1127. Min Act: -0.0000

Data Index: 1289291 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 2.1973. Min Range: -2.1973

Max Act: 1.2011. Min Act: -0.0000

Data Index: 204943 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 2.1973. Min Range: -2.1973

Max Act: 1.0368. Min Act: -0.0000

Data Index: 859707 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 2.1973. Min Range: -2.1973

Max Act: 1.1682. Min Act: -0.0000

Data Index: 676360 (C4 (Web Text))

Max Activating Token Index: 416