Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 132 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0793. Min Act: -0.0003

Data Index: 917849 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0687. Min Act: -0.0003

Data Index: 725288 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0661. Min Act: -0.0003

Data Index: 1226071 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0690. Min Act: -0.0003

Data Index: 912050 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0601. Min Act: -0.0003

Data Index: 1147069 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0632. Min Act: -0.0003

Data Index: 430195 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0627. Min Act: -0.0003

Data Index: 1020136 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0625. Min Act: -0.0003

Data Index: 340280 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0612. Min Act: -0.0003

Data Index: 629194 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0626. Min Act: -0.0003

Data Index: 952020 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0601. Min Act: -0.0003

Data Index: 1095772 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0619. Min Act: -0.0003

Data Index: 797578 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0618. Min Act: -0.0003

Data Index: 362575 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0605. Min Act: -0.0003

Data Index: 791778 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0626. Min Act: -0.0003

Data Index: 1008094 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0615. Min Act: -0.0003

Data Index: 1163635 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0619. Min Act: -0.0003

Data Index: 885265 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0624. Min Act: -0.0003

Data Index: 735420 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0586. Min Act: -0.0003

Data Index: 414595 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0578. Min Act: -0.0003

Data Index: 1070877 (C4 (Web Text))

Max Activating Token Index: 525