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

Dataset: The Pile

Neuron 2319 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: 1.2648. Min Range: -1.2648

Max Act: 1.2648. Min Act: -0.0000

Data Index: 1178083 (The Pile)

Max Activating Token Index: 137

Text #1

Max Range: 1.2648. Min Range: -1.2648

Max Act: 1.1151. Min Act: -0.0000

Data Index: 1064812 (The Pile)

Max Activating Token Index: 339

Text #2

Max Range: 1.2648. Min Range: -1.2648

Max Act: 1.0242. Min Act: -0.0000

Data Index: 1670331 (The Pile)

Max Activating Token Index: 925

Text #3

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.9744. Min Act: -0.0000

Data Index: 531833 (The Pile)

Max Activating Token Index: 265

Text #4

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.9791. Min Act: -0.0000

Data Index: 445612 (The Pile)

Max Activating Token Index: 724

Text #5

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.9965. Min Act: -0.0000

Data Index: 762276 (The Pile)

Max Activating Token Index: 669

Text #6

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.9235. Min Act: -0.0000

Data Index: 439028 (The Pile)

Max Activating Token Index: 54

Text #7

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.9744. Min Act: -0.0000

Data Index: 506652 (The Pile)

Max Activating Token Index: 743

Text #8

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.9390. Min Act: -0.0000

Data Index: 665012 (The Pile)

Max Activating Token Index: 324

Text #9

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.9474. Min Act: -0.0000

Data Index: 1776778 (The Pile)

Max Activating Token Index: 297

Text #10

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.8843. Min Act: -0.0000

Data Index: 654039 (The Pile)

Max Activating Token Index: 159

Text #11

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.9073. Min Act: -0.0000

Data Index: 833960 (The Pile)

Max Activating Token Index: 136

Text #12

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.8693. Min Act: -0.0000

Data Index: 935656 (The Pile)

Max Activating Token Index: 284

Text #13

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.8923. Min Act: -0.0000

Data Index: 1799708 (The Pile)

Max Activating Token Index: 259

Text #14

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1021960 (The Pile)

Max Activating Token Index: 214

Text #15

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.8807. Min Act: -0.0000

Data Index: 507019 (The Pile)

Max Activating Token Index: 452

Text #16

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.9007. Min Act: -0.0000

Data Index: 292299 (The Pile)

Max Activating Token Index: 850

Text #17

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.8959. Min Act: -0.0000

Data Index: 1085374 (The Pile)

Max Activating Token Index: 969

Text #18

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.8718. Min Act: -0.0000

Data Index: 299675 (The Pile)

Max Activating Token Index: 98

Text #19

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.8682. Min Act: -0.0000

Data Index: 598450 (The Pile)

Max Activating Token Index: 663