Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4657 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1244995 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.4667. Min Act: -0.0000

Data Index: 967008 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.4569. Min Act: -0.0000

Data Index: 1045540 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.4193. Min Act: -0.0000

Data Index: 150000 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.3796. Min Act: -0.0000

Data Index: 202168 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.3760. Min Act: -0.0000

Data Index: 945324 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.3856. Min Act: -0.0000

Data Index: 1225747 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.3725. Min Act: -0.0000

Data Index: 124912 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.3429. Min Act: -0.0000

Data Index: 702050 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.3645. Min Act: -0.0000

Data Index: 707228 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.3318. Min Act: -0.0000

Data Index: 675451 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.3478. Min Act: -0.0000

Data Index: 553849 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.3332. Min Act: -0.0000

Data Index: 1046598 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.3481. Min Act: -0.0000

Data Index: 95487 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.3448. Min Act: -0.0000

Data Index: 510573 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.2974. Min Act: -0.0000

Data Index: 554516 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.3067. Min Act: -0.0000

Data Index: 549063 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.3262. Min Act: -0.0000

Data Index: 529683 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.3310. Min Act: -0.0000

Data Index: 904208 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 0.5389. Min Range: -0.5389

Max Act: 0.2822. Min Act: -0.0000

Data Index: 1163338 (C4 (Web Text))

Max Activating Token Index: 214