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

Dataset: The Pile

Neuron 3782 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.2678. Min Act: -0.0000

Data Index: 1414609 (The Pile)

Max Activating Token Index: 328

Text #1

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.2417. Min Act: -0.0000

Data Index: 1942553 (The Pile)

Max Activating Token Index: 886

Text #2

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.1369. Min Act: -0.0000

Data Index: 636572 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.1215. Min Act: -0.0000

Data Index: 1089598 (The Pile)

Max Activating Token Index: 334

Text #4

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.0531. Min Act: -0.0000

Data Index: 361924 (The Pile)

Max Activating Token Index: 132

Text #5

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.0534. Min Act: -0.0000

Data Index: 53806 (The Pile)

Max Activating Token Index: 59

Text #6

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.0179. Min Act: -0.0000

Data Index: 1776181 (The Pile)

Max Activating Token Index: 857

Text #7

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.0118. Min Act: -0.0000

Data Index: 1967954 (The Pile)

Max Activating Token Index: 311

Text #8

Max Range: 1.2678. Min Range: -1.2678

Max Act: 0.9516. Min Act: -0.0000

Data Index: 434027 (The Pile)

Max Activating Token Index: 250

Text #9

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.0117. Min Act: -0.0000

Data Index: 1585853 (The Pile)

Max Activating Token Index: 906

Text #10

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.0064. Min Act: -0.0000

Data Index: 658180 (The Pile)

Max Activating Token Index: 135

Text #11

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.0044. Min Act: -0.0000

Data Index: 970639 (The Pile)

Max Activating Token Index: 530

Text #12

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.0146. Min Act: -0.0000

Data Index: 1128088 (The Pile)

Max Activating Token Index: 579

Text #13

Max Range: 1.2678. Min Range: -1.2678

Max Act: 0.9741. Min Act: -0.0000

Data Index: 682091 (The Pile)

Max Activating Token Index: 965

Text #14

Max Range: 1.2678. Min Range: -1.2678

Max Act: 0.9452. Min Act: -0.0000

Data Index: 957321 (The Pile)

Max Activating Token Index: 648

Text #15

Max Range: 1.2678. Min Range: -1.2678

Max Act: 0.9285. Min Act: -0.0000

Data Index: 305985 (The Pile)

Max Activating Token Index: 671

Text #16

Max Range: 1.2678. Min Range: -1.2678

Max Act: 0.9565. Min Act: -0.0000

Data Index: 309449 (The Pile)

Max Activating Token Index: 718

Text #17

Max Range: 1.2678. Min Range: -1.2678

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1714027 (The Pile)

Max Activating Token Index: 634

Text #18

Max Range: 1.2678. Min Range: -1.2678

Max Act: 0.9441. Min Act: -0.0000

Data Index: 1153213 (The Pile)

Max Activating Token Index: 310

Text #19

Max Range: 1.2678. Min Range: -1.2678

Max Act: 0.9406. Min Act: -0.0000

Data Index: 1110701 (The Pile)

Max Activating Token Index: 240