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

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

Neuron 4358 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4464. Min Range: -3.4464

Max Act: 3.4293. Min Act: -0.0001

Data Index: 57259 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 3.4464. Min Range: -3.4464

Max Act: 3.2513. Min Act: -0.0000

Data Index: 1279476 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 3.4464. Min Range: -3.4464

Max Act: 3.0473. Min Act: -0.0000

Data Index: 202387 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 3.4464. Min Range: -3.4464

Max Act: 3.3380. Min Act: -0.0000

Data Index: 1183199 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 3.4464. Min Range: -3.4464

Max Act: 3.0205. Min Act: -0.0000

Data Index: 1204636 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 3.4464. Min Range: -3.4464

Max Act: 3.3115. Min Act: -0.0000

Data Index: 537430 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 3.4464. Min Range: -3.4464

Max Act: 3.3197. Min Act: -0.0001

Data Index: 377126 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 3.4464. Min Range: -3.4464

Max Act: 3.0388. Min Act: -0.0000

Data Index: 1345436 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 3.4464. Min Range: -3.4464

Max Act: 3.1614. Min Act: -0.0000

Data Index: 1074248 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 3.4464. Min Range: -3.4464

Max Act: 3.4464. Min Act: -0.0000

Data Index: 121292 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 3.4464. Min Range: -3.4464

Max Act: 3.3760. Min Act: -0.0000

Data Index: 423795 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 3.4464. Min Range: -3.4464

Max Act: 3.2316. Min Act: -0.0001

Data Index: 865894 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 3.4464. Min Range: -3.4464

Max Act: 2.7981. Min Act: -0.0001

Data Index: 1280202 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 3.4464. Min Range: -3.4464

Max Act: 3.0594. Min Act: -0.0001

Data Index: 405603 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 3.4464. Min Range: -3.4464

Max Act: 3.0508. Min Act: -0.0000

Data Index: 395327 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 3.4464. Min Range: -3.4464

Max Act: 3.1743. Min Act: -0.0001

Data Index: 144354 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 3.4464. Min Range: -3.4464

Max Act: 3.0414. Min Act: -0.0001

Data Index: 1289107 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 3.4464. Min Range: -3.4464

Max Act: 3.0856. Min Act: -0.0001

Data Index: 890814 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 3.4464. Min Range: -3.4464

Max Act: 2.9651. Min Act: -0.0001

Data Index: 1298020 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 3.4464. Min Range: -3.4464

Max Act: 2.9599. Min Act: -0.0001

Data Index: 381595 (C4 (Web Text))

Max Activating Token Index: 640