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

Dataset: The Pile

Neuron 2253 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.6492. Min Act: -0.0000

Data Index: 1848663 (The Pile)

Max Activating Token Index: 683

Text #1

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.8272. Min Act: -0.0000

Data Index: 456581 (The Pile)

Max Activating Token Index: 399

Text #2

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.7019. Min Act: -0.0000

Data Index: 1592762 (The Pile)

Max Activating Token Index: 788

Text #3

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.6526. Min Act: -0.0000

Data Index: 1075743 (The Pile)

Max Activating Token Index: 469

Text #4

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.5893. Min Act: -0.0000

Data Index: 1787201 (The Pile)

Max Activating Token Index: 416

Text #5

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4879. Min Act: -0.0000

Data Index: 1776196 (The Pile)

Max Activating Token Index: 703

Text #6

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.5908. Min Act: -0.0000

Data Index: 1543045 (The Pile)

Max Activating Token Index: 350

Text #7

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4731. Min Act: -0.0000

Data Index: 1389139 (The Pile)

Max Activating Token Index: 672

Text #8

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.5450. Min Act: -0.0000

Data Index: 1364321 (The Pile)

Max Activating Token Index: 901

Text #9

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.3585. Min Act: -0.0000

Data Index: 394539 (The Pile)

Max Activating Token Index: 976

Text #10

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4863. Min Act: -0.0000

Data Index: 1050647 (The Pile)

Max Activating Token Index: 492

Text #11

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.5491. Min Act: -0.0000

Data Index: 92930 (The Pile)

Max Activating Token Index: 469

Text #12

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4695. Min Act: -0.0000

Data Index: 998637 (The Pile)

Max Activating Token Index: 639

Text #13

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.3990. Min Act: -0.0000

Data Index: 1411688 (The Pile)

Max Activating Token Index: 909

Text #14

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.3621. Min Act: -0.0000

Data Index: 182971 (The Pile)

Max Activating Token Index: 419

Text #15

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.3609. Min Act: -0.0000

Data Index: 1692430 (The Pile)

Max Activating Token Index: 365

Text #16

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.4656. Min Act: -0.0000

Data Index: 1128000 (The Pile)

Max Activating Token Index: 162

Text #17

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.3808. Min Act: -0.0000

Data Index: 1242227 (The Pile)

Max Activating Token Index: 247

Text #18

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.3570. Min Act: -0.0000

Data Index: 962436 (The Pile)

Max Activating Token Index: 597

Text #19

Max Range: 1.8272. Min Range: -1.8272

Max Act: 1.3513. Min Act: -0.0000

Data Index: 802978 (The Pile)

Max Activating Token Index: 279