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

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

Neuron 853 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1625. Min Act: -0.0001

Data Index: 143130 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1593. Min Act: -0.0001

Data Index: 1005473 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1597. Min Act: -0.0001

Data Index: 283499 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1475. Min Act: -0.0001

Data Index: 693732 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1646. Min Act: -0.0001

Data Index: 1311328 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1413. Min Act: -0.0001

Data Index: 1219245 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1369. Min Act: -0.0001

Data Index: 332940 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1347. Min Act: -0.0001

Data Index: 110873 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1307. Min Act: -0.0001

Data Index: 630659 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1602. Min Act: -0.0001

Data Index: 2301 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1326. Min Act: -0.0001

Data Index: 731711 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1412. Min Act: -0.0001

Data Index: 1036601 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1221. Min Act: -0.0001

Data Index: 199834 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1370. Min Act: -0.0001

Data Index: 551272 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1288. Min Act: -0.0001

Data Index: 800801 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1486. Min Act: -0.0001

Data Index: 1099396 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1339. Min Act: -0.0001

Data Index: 937372 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1326. Min Act: -0.0001

Data Index: 443372 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1254. Min Act: -0.0001

Data Index: 1238465 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1251. Min Act: -0.0001

Data Index: 790104 (C4 (Web Text))

Max Activating Token Index: 410