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

Dataset: The Pile

Neuron 1685 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.3873. Min Act: -0.0000

Data Index: 630266 (The Pile)

Max Activating Token Index: 477

Text #1

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1267956 (The Pile)

Max Activating Token Index: 228

Text #2

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1069113 (The Pile)

Max Activating Token Index: 221

Text #3

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.7519. Min Act: -0.0000

Data Index: 1574918 (The Pile)

Max Activating Token Index: 498

Text #4

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.6650. Min Act: -0.0000

Data Index: 909576 (The Pile)

Max Activating Token Index: 675

Text #5

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.6501. Min Act: -0.0000

Data Index: 340369 (The Pile)

Max Activating Token Index: 142

Text #6

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1314790 (The Pile)

Max Activating Token Index: 777

Text #7

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.6980. Min Act: -0.0000

Data Index: 204529 (The Pile)

Max Activating Token Index: 444

Text #8

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.7213. Min Act: -0.0000

Data Index: 470719 (The Pile)

Max Activating Token Index: 71

Text #9

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1574583 (The Pile)

Max Activating Token Index: 498

Text #10

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.5230. Min Act: -0.0000

Data Index: 193300 (The Pile)

Max Activating Token Index: 718

Text #11

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.7349. Min Act: -0.0000

Data Index: 48479 (The Pile)

Max Activating Token Index: 551

Text #12

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1155025 (The Pile)

Max Activating Token Index: 609

Text #13

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.6487. Min Act: -0.0000

Data Index: 360876 (The Pile)

Max Activating Token Index: 323

Text #14

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.5936. Min Act: -0.0000

Data Index: 1024820 (The Pile)

Max Activating Token Index: 409

Text #15

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1890329 (The Pile)

Max Activating Token Index: 431

Text #16

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1586998 (The Pile)

Max Activating Token Index: 979

Text #17

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.5389. Min Act: -0.0000

Data Index: 471948 (The Pile)

Max Activating Token Index: 374

Text #18

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.5745. Min Act: -0.0000

Data Index: 1894491 (The Pile)

Max Activating Token Index: 377

Text #19

Max Range: 1.3873. Min Range: -1.3873

Max Act: 0.5603. Min Act: -0.0000

Data Index: 1732162 (The Pile)

Max Activating Token Index: 190