Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1165 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0831. Min Act: -0.0003

Data Index: 1227521 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0818. Min Act: -0.0003

Data Index: 530926 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0783. Min Act: -0.0003

Data Index: 160634 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0745. Min Act: -0.0003

Data Index: 575903 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0751. Min Act: -0.0003

Data Index: 774138 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0730. Min Act: -0.0003

Data Index: 806389 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0694. Min Act: -0.0003

Data Index: 90732 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0694. Min Act: -0.0003

Data Index: 745011 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0694. Min Act: -0.0003

Data Index: 416159 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0694. Min Act: -0.0003

Data Index: 223869 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0677. Min Act: -0.0003

Data Index: 1139650 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0685. Min Act: -0.0003

Data Index: 418020 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0681. Min Act: -0.0003

Data Index: 1175160 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0647. Min Act: -0.0004

Data Index: 435529 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0651. Min Act: -0.0003

Data Index: 444245 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0656. Min Act: -0.0003

Data Index: 526600 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0638. Min Act: -0.0003

Data Index: 270914 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0656. Min Act: -0.0002

Data Index: 942127 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0655. Min Act: -0.0003

Data Index: 829735 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0641. Min Act: -0.0003

Data Index: 534455 (C4 (Web Text))

Max Activating Token Index: 382