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

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

Neuron 1704 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.6585. Min Act: -0.0000

Data Index: 1334004 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.6153. Min Act: -0.0000

Data Index: 51985 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5496. Min Act: -0.0001

Data Index: 412637 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.4931. Min Act: -0.0001

Data Index: 492534 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5587. Min Act: -0.0000

Data Index: 15439 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5555. Min Act: -0.0001

Data Index: 961598 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5389. Min Act: -0.0000

Data Index: 664631 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5912. Min Act: -0.0000

Data Index: 224907 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5363. Min Act: -0.0000

Data Index: 440074 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5688. Min Act: -0.0000

Data Index: 357470 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5487. Min Act: -0.0001

Data Index: 987622 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.4967. Min Act: -0.0001

Data Index: 46618 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5295. Min Act: -0.0001

Data Index: 638013 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5375. Min Act: -0.0000

Data Index: 1163877 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5385. Min Act: -0.0000

Data Index: 988754 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5399. Min Act: -0.0000

Data Index: 304150 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5339. Min Act: -0.0001

Data Index: 177671 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5107. Min Act: -0.0001

Data Index: 91277 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5320. Min Act: -0.0001

Data Index: 1308420 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 0.6585. Min Range: -0.6585

Max Act: 0.5203. Min Act: -0.0000

Data Index: 992537 (C4 (Web Text))

Max Activating Token Index: 974