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

Dataset: The Pile

Neuron 937 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: 1.7215. Min Range: -1.7215

Max Act: 1.7215. Min Act: -0.0000

Data Index: 653736 (The Pile)

Max Activating Token Index: 75

Text #1

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.6165. Min Act: -0.0000

Data Index: 859228 (The Pile)

Max Activating Token Index: 271

Text #2

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.5273. Min Act: -0.0000

Data Index: 420401 (The Pile)

Max Activating Token Index: 700

Text #3

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.4913. Min Act: -0.0000

Data Index: 1497050 (The Pile)

Max Activating Token Index: 366

Text #4

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.4542. Min Act: -0.0000

Data Index: 1116015 (The Pile)

Max Activating Token Index: 558

Text #5

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.4474. Min Act: -0.0000

Data Index: 1993654 (The Pile)

Max Activating Token Index: 1012

Text #6

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.3912. Min Act: -0.0000

Data Index: 21447 (The Pile)

Max Activating Token Index: 353

Text #7

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.3018. Min Act: -0.0000

Data Index: 1184446 (The Pile)

Max Activating Token Index: 603

Text #8

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.4535. Min Act: -0.0000

Data Index: 325266 (The Pile)

Max Activating Token Index: 151

Text #9

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.3598. Min Act: -0.0000

Data Index: 119199 (The Pile)

Max Activating Token Index: 663

Text #10

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.3750. Min Act: -0.0000

Data Index: 1245678 (The Pile)

Max Activating Token Index: 282

Text #11

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.3373. Min Act: -0.0000

Data Index: 953383 (The Pile)

Max Activating Token Index: 302

Text #12

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.3232. Min Act: -0.0000

Data Index: 1122668 (The Pile)

Max Activating Token Index: 234

Text #13

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.3108. Min Act: -0.0000

Data Index: 684880 (The Pile)

Max Activating Token Index: 963

Text #14

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.3170. Min Act: -0.0000

Data Index: 1473534 (The Pile)

Max Activating Token Index: 683

Text #15

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.2060. Min Act: -0.0000

Data Index: 605010 (The Pile)

Max Activating Token Index: 498

Text #16

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.2336. Min Act: -0.0000

Data Index: 1186380 (The Pile)

Max Activating Token Index: 982

Text #17

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.3068. Min Act: -0.0000

Data Index: 280707 (The Pile)

Max Activating Token Index: 865

Text #18

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.3112. Min Act: -0.0000

Data Index: 1764588 (The Pile)

Max Activating Token Index: 588

Text #19

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.3783. Min Act: -0.0000

Data Index: 1561569 (The Pile)

Max Activating Token Index: 83