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

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

Neuron 3724 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.3470. Min Act: -0.0000

Data Index: 970471 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.3248. Min Act: -0.0000

Data Index: 372051 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.3082. Min Act: -0.0000

Data Index: 1022114 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.3126. Min Act: -0.0000

Data Index: 528608 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.3044. Min Act: -0.0001

Data Index: 1028679 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2866. Min Act: -0.0001

Data Index: 919861 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2696. Min Act: -0.0000

Data Index: 826536 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2600. Min Act: -0.0000

Data Index: 892621 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2660. Min Act: -0.0000

Data Index: 255642 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2484. Min Act: -0.0000

Data Index: 248648 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2557. Min Act: -0.0000

Data Index: 729505 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2526. Min Act: -0.0000

Data Index: 946117 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2534. Min Act: -0.0000

Data Index: 19965 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1329073 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2378. Min Act: -0.0000

Data Index: 358397 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2374. Min Act: -0.0000

Data Index: 1284577 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2389. Min Act: -0.0001

Data Index: 951230 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2444. Min Act: -0.0001

Data Index: 854509 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2421. Min Act: -0.0001

Data Index: 1031661 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2421. Min Act: -0.0000

Data Index: 994332 (C4 (Web Text))

Max Activating Token Index: 152