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

Dataset: The Pile

Neuron 685 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: 0.5026. Min Range: -0.5026

Max Act: 0.5026. Min Act: -0.0000

Data Index: 734302 (The Pile)

Max Activating Token Index: 321

Text #1

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.4588. Min Act: -0.0000

Data Index: 274210 (The Pile)

Max Activating Token Index: 382

Text #2

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.4861. Min Act: -0.0000

Data Index: 1528865 (The Pile)

Max Activating Token Index: 322

Text #3

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.4804. Min Act: -0.0000

Data Index: 1148859 (The Pile)

Max Activating Token Index: 235

Text #4

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.4421. Min Act: -0.0000

Data Index: 840135 (The Pile)

Max Activating Token Index: 495

Text #5

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.4012. Min Act: -0.0000

Data Index: 634976 (The Pile)

Max Activating Token Index: 213

Text #6

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.4282. Min Act: -0.0000

Data Index: 620606 (The Pile)

Max Activating Token Index: 421

Text #7

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.3853. Min Act: -0.0000

Data Index: 1504401 (The Pile)

Max Activating Token Index: 680

Text #8

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.3894. Min Act: -0.0000

Data Index: 696323 (The Pile)

Max Activating Token Index: 240

Text #9

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.3831. Min Act: -0.0000

Data Index: 154453 (The Pile)

Max Activating Token Index: 161

Text #10

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1672818 (The Pile)

Max Activating Token Index: 173

Text #11

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.3527. Min Act: -0.0000

Data Index: 50423 (The Pile)

Max Activating Token Index: 202

Text #12

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.3618. Min Act: -0.0000

Data Index: 1811199 (The Pile)

Max Activating Token Index: 127

Text #13

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1071739 (The Pile)

Max Activating Token Index: 626

Text #14

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.3429. Min Act: -0.0000

Data Index: 1410557 (The Pile)

Max Activating Token Index: 146

Text #15

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.3623. Min Act: -0.0000

Data Index: 446019 (The Pile)

Max Activating Token Index: 86

Text #16

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1570189 (The Pile)

Max Activating Token Index: 645

Text #17

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1154018 (The Pile)

Max Activating Token Index: 551

Text #18

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.2745. Min Act: -0.0000

Data Index: 80667 (The Pile)

Max Activating Token Index: 799

Text #19

Max Range: 0.5026. Min Range: -0.5026

Max Act: 0.2851. Min Act: -0.0000

Data Index: 762851 (The Pile)

Max Activating Token Index: 194