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

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

Neuron 3304 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3222. Min Range: -0.3222

Max Act: 0.3222. Min Act: -0.0001

Data Index: 763457 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.3222. Min Range: -0.3222

Max Act: 0.2627. Min Act: -0.0001

Data Index: 693357 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.3222. Min Range: -0.3222

Max Act: 0.2362. Min Act: -0.0001

Data Index: 924491 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.3222. Min Range: -0.3222

Max Act: 0.1676. Min Act: -0.0001

Data Index: 844652 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.3222. Min Range: -0.3222

Max Act: 0.1684. Min Act: -0.0001

Data Index: 555831 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.3222. Min Range: -0.3222

Max Act: 0.1522. Min Act: -0.0001

Data Index: 94688 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.3222. Min Range: -0.3222

Max Act: 0.1612. Min Act: -0.0001

Data Index: 122310 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.3222. Min Range: -0.3222

Max Act: 0.1625. Min Act: -0.0001

Data Index: 876932 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 0.3222. Min Range: -0.3222

Max Act: 0.1570. Min Act: -0.0001

Data Index: 616109 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.3222. Min Range: -0.3222

Max Act: 0.1572. Min Act: -0.0001

Data Index: 760513 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.3222. Min Range: -0.3222

Max Act: 0.1500. Min Act: -0.0001

Data Index: 556160 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.3222. Min Range: -0.3222

Max Act: 0.1559. Min Act: -0.0001

Data Index: 537723 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.3222. Min Range: -0.3222

Max Act: 0.1400. Min Act: -0.0001

Data Index: 119699 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 0.3222. Min Range: -0.3222

Max Act: 0.1544. Min Act: -0.0001

Data Index: 1078509 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 0.3222. Min Range: -0.3222

Max Act: 0.1469. Min Act: -0.0001

Data Index: 153909 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.3222. Min Range: -0.3222

Max Act: 0.1472. Min Act: -0.0001

Data Index: 886937 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.3222. Min Range: -0.3222

Max Act: 0.1560. Min Act: -0.0001

Data Index: 330110 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.3222. Min Range: -0.3222

Max Act: 0.1399. Min Act: -0.0001

Data Index: 593177 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.3222. Min Range: -0.3222

Max Act: 0.1515. Min Act: -0.0001

Data Index: 1165313 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.3222. Min Range: -0.3222

Max Act: 0.1423. Min Act: -0.0001

Data Index: 1065112 (C4 (Web Text))

Max Activating Token Index: 413