Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 162 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0671. Min Act: -0.0003

Data Index: 449241 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0636. Min Act: -0.0003

Data Index: 917818 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0620. Min Act: -0.0003

Data Index: 1163833 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0587. Min Act: -0.0003

Data Index: 1027345 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0576. Min Act: -0.0004

Data Index: 507968 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0574. Min Act: -0.0003

Data Index: 504424 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0548. Min Act: -0.0003

Data Index: 1336729 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0558. Min Act: -0.0003

Data Index: 706926 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0537. Min Act: -0.0003

Data Index: 1357431 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0558. Min Act: -0.0003

Data Index: 1104729 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0554. Min Act: -0.0003

Data Index: 875859 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1152999 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0545. Min Act: -0.0002

Data Index: 406051 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0530. Min Act: -0.0003

Data Index: 584802 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0536. Min Act: -0.0003

Data Index: 1272376 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0523. Min Act: -0.0003

Data Index: 1246346 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0510. Min Act: -0.0003

Data Index: 668742 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0519. Min Act: -0.0003

Data Index: 454910 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0539. Min Act: -0.0003

Data Index: 554266 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0517. Min Act: -0.0003

Data Index: 784466 (C4 (Web Text))

Max Activating Token Index: 183