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

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

Neuron 4496 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0931. Min Range: -1.0931

Max Act: 1.0931. Min Act: -0.0001

Data Index: 527298 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 1.0931. Min Range: -1.0931

Max Act: 0.9496. Min Act: -0.0001

Data Index: 601977 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 1.0931. Min Range: -1.0931

Max Act: 0.8300. Min Act: -0.0001

Data Index: 867172 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 1.0931. Min Range: -1.0931

Max Act: 0.7599. Min Act: -0.0001

Data Index: 1267695 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 1.0931. Min Range: -1.0931

Max Act: 0.7628. Min Act: -0.0001

Data Index: 581338 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 1.0931. Min Range: -1.0931

Max Act: 0.7899. Min Act: -0.0001

Data Index: 515240 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 1.0931. Min Range: -1.0931

Max Act: 0.7693. Min Act: -0.0001

Data Index: 1100399 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 1.0931. Min Range: -1.0931

Max Act: 0.7690. Min Act: -0.0001

Data Index: 786090 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 1.0931. Min Range: -1.0931

Max Act: 0.7237. Min Act: -0.0001

Data Index: 1092615 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 1.0931. Min Range: -1.0931

Max Act: 0.6833. Min Act: -0.0001

Data Index: 1275386 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 1.0931. Min Range: -1.0931

Max Act: 0.6847. Min Act: -0.0001

Data Index: 497307 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 1.0931. Min Range: -1.0931

Max Act: 0.6504. Min Act: -0.0001

Data Index: 458857 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 1.0931. Min Range: -1.0931

Max Act: 0.5671. Min Act: -0.0001

Data Index: 815834 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 1.0931. Min Range: -1.0931

Max Act: 0.6131. Min Act: -0.0001

Data Index: 901215 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 1.0931. Min Range: -1.0931

Max Act: 0.6319. Min Act: -0.0001

Data Index: 1344726 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 1.0931. Min Range: -1.0931

Max Act: 0.5897. Min Act: -0.0001

Data Index: 20082 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 1.0931. Min Range: -1.0931

Max Act: 0.5967. Min Act: -0.0001

Data Index: 1357018 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 1.0931. Min Range: -1.0931

Max Act: 0.5734. Min Act: -0.0001

Data Index: 488393 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 1.0931. Min Range: -1.0931

Max Act: 0.5809. Min Act: -0.0001

Data Index: 1258853 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 1.0931. Min Range: -1.0931

Max Act: 0.5777. Min Act: -0.0002

Data Index: 345084 (C4 (Web Text))

Max Activating Token Index: 534