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

Dataset: The Pile

Neuron 979 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: 0.6392. Min Range: -0.6392

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1965458 (The Pile)

Max Activating Token Index: 113

Text #1

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.6392. Min Act: -0.0000

Data Index: 437069 (The Pile)

Max Activating Token Index: 323

Text #2

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.6248. Min Act: -0.0000

Data Index: 813732 (The Pile)

Max Activating Token Index: 312

Text #3

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1423410 (The Pile)

Max Activating Token Index: 456

Text #4

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1406980 (The Pile)

Max Activating Token Index: 611

Text #5

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5747. Min Act: -0.0000

Data Index: 1392408 (The Pile)

Max Activating Token Index: 850

Text #6

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1308673 (The Pile)

Max Activating Token Index: 703

Text #7

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5407. Min Act: -0.0000

Data Index: 189617 (The Pile)

Max Activating Token Index: 204

Text #8

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5438. Min Act: -0.0000

Data Index: 631800 (The Pile)

Max Activating Token Index: 364

Text #9

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.4918. Min Act: -0.0000

Data Index: 178639 (The Pile)

Max Activating Token Index: 652

Text #10

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5307. Min Act: -0.0000

Data Index: 145478 (The Pile)

Max Activating Token Index: 539

Text #11

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5275. Min Act: -0.0000

Data Index: 43035 (The Pile)

Max Activating Token Index: 91

Text #12

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.4773. Min Act: -0.0000

Data Index: 915766 (The Pile)

Max Activating Token Index: 169

Text #13

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5322. Min Act: -0.0000

Data Index: 158644 (The Pile)

Max Activating Token Index: 452

Text #14

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5336. Min Act: -0.0000

Data Index: 991101 (The Pile)

Max Activating Token Index: 445

Text #15

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5288. Min Act: -0.0000

Data Index: 293883 (The Pile)

Max Activating Token Index: 194

Text #16

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1324908 (The Pile)

Max Activating Token Index: 993

Text #17

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5283. Min Act: -0.0000

Data Index: 1062107 (The Pile)

Max Activating Token Index: 223

Text #18

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5743. Min Act: -0.0000

Data Index: 1515143 (The Pile)

Max Activating Token Index: 1005

Text #19

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5060. Min Act: -0.0000

Data Index: 56480 (The Pile)

Max Activating Token Index: 276