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

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

Neuron 2874 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1495. Min Range: -1.1495

Max Act: 1.1495. Min Act: -0.0000

Data Index: 297137 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.9526. Min Act: -0.0000

Data Index: 98420 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 1.1495. Min Range: -1.1495

Max Act: 1.0246. Min Act: -0.0000

Data Index: 475557 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.9397. Min Act: -0.0000

Data Index: 532862 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1028679 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.8463. Min Act: -0.0000

Data Index: 573602 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.8709. Min Act: -0.0000

Data Index: 835347 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.8612. Min Act: -0.0000

Data Index: 382308 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.8476. Min Act: -0.0000

Data Index: 1224341 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.8520. Min Act: -0.0000

Data Index: 967926 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.8212. Min Act: -0.0000

Data Index: 771769 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.8393. Min Act: -0.0000

Data Index: 540037 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.8120. Min Act: -0.0000

Data Index: 87228 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.7724. Min Act: -0.0000

Data Index: 988234 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.8025. Min Act: -0.0000

Data Index: 496591 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.7318. Min Act: -0.0000

Data Index: 112463 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.7869. Min Act: -0.0000

Data Index: 320401 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.7966. Min Act: -0.0000

Data Index: 485042 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.7741. Min Act: -0.0000

Data Index: 732920 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.7946. Min Act: -0.0000

Data Index: 567400 (C4 (Web Text))

Max Activating Token Index: 517