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

Dataset: The Pile

Neuron 4837 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.6691. Min Act: -0.0000

Data Index: 202022 (The Pile)

Max Activating Token Index: 710

Text #1

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.5560. Min Act: -0.0000

Data Index: 631758 (The Pile)

Max Activating Token Index: 577

Text #2

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4759. Min Act: -0.0000

Data Index: 740480 (The Pile)

Max Activating Token Index: 152

Text #3

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4020. Min Act: -0.0000

Data Index: 1396232 (The Pile)

Max Activating Token Index: 397

Text #4

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3719. Min Act: -0.0000

Data Index: 1722873 (The Pile)

Max Activating Token Index: 163

Text #5

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3505. Min Act: -0.0000

Data Index: 801761 (The Pile)

Max Activating Token Index: 372

Text #6

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4207. Min Act: -0.0000

Data Index: 512208 (The Pile)

Max Activating Token Index: 338

Text #7

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4890. Min Act: -0.0000

Data Index: 695886 (The Pile)

Max Activating Token Index: 612

Text #8

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3149. Min Act: -0.0000

Data Index: 1533868 (The Pile)

Max Activating Token Index: 279

Text #9

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3153. Min Act: -0.0000

Data Index: 421337 (The Pile)

Max Activating Token Index: 602

Text #10

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3544. Min Act: -0.0000

Data Index: 268222 (The Pile)

Max Activating Token Index: 479

Text #11

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3126. Min Act: -0.0000

Data Index: 977068 (The Pile)

Max Activating Token Index: 300

Text #12

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.2427. Min Act: -0.0000

Data Index: 499111 (The Pile)

Max Activating Token Index: 293

Text #13

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.0781. Min Act: -0.0000

Data Index: 1636051 (The Pile)

Max Activating Token Index: 641

Text #14

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.1730. Min Act: -0.0000

Data Index: 1624929 (The Pile)

Max Activating Token Index: 119

Text #15

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.2284. Min Act: -0.0000

Data Index: 1132316 (The Pile)

Max Activating Token Index: 568

Text #16

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.2187. Min Act: -0.0000

Data Index: 1750350 (The Pile)

Max Activating Token Index: 734

Text #17

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4288. Min Act: -0.0000

Data Index: 194320 (The Pile)

Max Activating Token Index: 685

Text #18

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.2095. Min Act: -0.0000

Data Index: 671359 (The Pile)

Max Activating Token Index: 165

Text #19

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.1254. Min Act: -0.0000

Data Index: 1905661 (The Pile)

Max Activating Token Index: 825