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

Dataset: The Pile

Neuron 1416 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.8279. Min Act: -0.0000

Data Index: 760676 (The Pile)

Max Activating Token Index: 817

Text #1

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.6416. Min Act: -0.0000

Data Index: 546197 (The Pile)

Max Activating Token Index: 593

Text #2

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.5965. Min Act: -0.0000

Data Index: 516913 (The Pile)

Max Activating Token Index: 301

Text #3

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1988195 (The Pile)

Max Activating Token Index: 1022

Text #4

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.5013. Min Act: -0.0000

Data Index: 1323692 (The Pile)

Max Activating Token Index: 521

Text #5

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.4675. Min Act: -0.0000

Data Index: 1758835 (The Pile)

Max Activating Token Index: 708

Text #6

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.4996. Min Act: -0.0000

Data Index: 1754302 (The Pile)

Max Activating Token Index: 241

Text #7

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.4296. Min Act: -0.0000

Data Index: 1822695 (The Pile)

Max Activating Token Index: 836

Text #8

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.4394. Min Act: -0.0000

Data Index: 524356 (The Pile)

Max Activating Token Index: 608

Text #9

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.4366. Min Act: -0.0000

Data Index: 115459 (The Pile)

Max Activating Token Index: 491

Text #10

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1359558 (The Pile)

Max Activating Token Index: 680

Text #11

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.4257. Min Act: -0.0000

Data Index: 1776311 (The Pile)

Max Activating Token Index: 611

Text #12

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.4127. Min Act: -0.0000

Data Index: 969084 (The Pile)

Max Activating Token Index: 568

Text #13

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.4205. Min Act: -0.0000

Data Index: 1082471 (The Pile)

Max Activating Token Index: 528

Text #14

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.4174. Min Act: -0.0000

Data Index: 1424240 (The Pile)

Max Activating Token Index: 634

Text #15

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.4275. Min Act: -0.0000

Data Index: 256286 (The Pile)

Max Activating Token Index: 458

Text #16

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.3916. Min Act: -0.0000

Data Index: 386844 (The Pile)

Max Activating Token Index: 120

Text #17

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.4240. Min Act: -0.0000

Data Index: 1082176 (The Pile)

Max Activating Token Index: 103

Text #18

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.3598. Min Act: -0.0000

Data Index: 751453 (The Pile)

Max Activating Token Index: 615

Text #19

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1239168 (The Pile)

Max Activating Token Index: 526