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

Dataset: The Pile

Neuron 2716 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.3595. Min Act: 0.0000

Data Index: 769232 (The Pile)

Max Activating Token Index: 907

Text #1

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1006. Min Act: -0.0000

Data Index: 567968 (The Pile)

Max Activating Token Index: 876

Text #2

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1657. Min Act: -0.0000

Data Index: 1706505 (The Pile)

Max Activating Token Index: 140

Text #3

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1118. Min Act: -0.0000

Data Index: 78312 (The Pile)

Max Activating Token Index: 372

Text #4

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1568. Min Act: -0.0000

Data Index: 134806 (The Pile)

Max Activating Token Index: 431

Text #5

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1441. Min Act: -0.0000

Data Index: 1900451 (The Pile)

Max Activating Token Index: 585

Text #6

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.0218. Min Act: -0.0000

Data Index: 97216 (The Pile)

Max Activating Token Index: 48

Text #7

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.0921. Min Act: -0.0000

Data Index: 1451490 (The Pile)

Max Activating Token Index: 95

Text #8

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.2145. Min Act: -0.0000

Data Index: 1189803 (The Pile)

Max Activating Token Index: 611

Text #9

Max Range: 1.3595. Min Range: -1.3595

Max Act: 0.9390. Min Act: 0.0000

Data Index: 1223038 (The Pile)

Max Activating Token Index: 987

Text #10

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.0149. Min Act: -0.0000

Data Index: 140716 (The Pile)

Max Activating Token Index: 891

Text #11

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.0127. Min Act: -0.0000

Data Index: 1278676 (The Pile)

Max Activating Token Index: 745

Text #12

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.0044. Min Act: -0.0000

Data Index: 1662703 (The Pile)

Max Activating Token Index: 851

Text #13

Max Range: 1.3595. Min Range: -1.3595

Max Act: 0.9689. Min Act: -0.0000

Data Index: 119893 (The Pile)

Max Activating Token Index: 958

Text #14

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.0441. Min Act: -0.0000

Data Index: 1133162 (The Pile)

Max Activating Token Index: 419

Text #15

Max Range: 1.3595. Min Range: -1.3595

Max Act: 0.9555. Min Act: -0.0000

Data Index: 1967314 (The Pile)

Max Activating Token Index: 182

Text #16

Max Range: 1.3595. Min Range: -1.3595

Max Act: 0.9812. Min Act: -0.0000

Data Index: 756985 (The Pile)

Max Activating Token Index: 888

Text #17

Max Range: 1.3595. Min Range: -1.3595

Max Act: 0.9164. Min Act: -0.0000

Data Index: 1671906 (The Pile)

Max Activating Token Index: 188

Text #18

Max Range: 1.3595. Min Range: -1.3595

Max Act: 0.9415. Min Act: -0.0000

Data Index: 348028 (The Pile)

Max Activating Token Index: 161

Text #19

Max Range: 1.3595. Min Range: -1.3595

Max Act: 0.9239. Min Act: -0.0000

Data Index: 732507 (The Pile)

Max Activating Token Index: 120