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

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

Neuron 4386 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.6119. Min Act: -0.0000

Data Index: 181011 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.6201. Min Act: -0.0000

Data Index: 444806 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1294469 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5454. Min Act: -0.0000

Data Index: 137 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5111. Min Act: -0.0000

Data Index: 975989 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4962. Min Act: -0.0000

Data Index: 601930 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4640. Min Act: -0.0000

Data Index: 630345 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5032. Min Act: -0.0000

Data Index: 551882 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4710. Min Act: -0.0000

Data Index: 12579 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4595. Min Act: -0.0000

Data Index: 658992 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5110. Min Act: -0.0000

Data Index: 939802 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4184. Min Act: -0.0000

Data Index: 948587 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4992. Min Act: -0.0000

Data Index: 440411 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4613. Min Act: -0.0000

Data Index: 273672 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4473. Min Act: -0.0000

Data Index: 1071334 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1295682 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4544. Min Act: -0.0000

Data Index: 364258 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4511. Min Act: -0.0000

Data Index: 266734 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.3937. Min Act: -0.0000

Data Index: 427969 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4092. Min Act: -0.0000

Data Index: 537657 (C4 (Web Text))

Max Activating Token Index: 872