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

Dataset: The Pile

Neuron 4705 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3952. Min Act: -0.0000

Data Index: 957842 (The Pile)

Max Activating Token Index: 528

Text #1

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1555147 (The Pile)

Max Activating Token Index: 230

Text #2

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3924. Min Act: -0.0000

Data Index: 854733 (The Pile)

Max Activating Token Index: 430

Text #3

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.4130. Min Act: -0.0000

Data Index: 873207 (The Pile)

Max Activating Token Index: 422

Text #4

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3815. Min Act: -0.0000

Data Index: 1116937 (The Pile)

Max Activating Token Index: 830

Text #5

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3618. Min Act: -0.0000

Data Index: 205260 (The Pile)

Max Activating Token Index: 17

Text #6

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3694. Min Act: -0.0000

Data Index: 1447345 (The Pile)

Max Activating Token Index: 346

Text #7

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3384. Min Act: -0.0000

Data Index: 65270 (The Pile)

Max Activating Token Index: 398

Text #8

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3594. Min Act: -0.0000

Data Index: 1090288 (The Pile)

Max Activating Token Index: 459

Text #9

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3602. Min Act: -0.0000

Data Index: 1838255 (The Pile)

Max Activating Token Index: 647

Text #10

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3542. Min Act: -0.0000

Data Index: 904270 (The Pile)

Max Activating Token Index: 435

Text #11

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3437. Min Act: -0.0000

Data Index: 560283 (The Pile)

Max Activating Token Index: 679

Text #12

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3386. Min Act: -0.0000

Data Index: 701955 (The Pile)

Max Activating Token Index: 675

Text #13

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3132. Min Act: -0.0000

Data Index: 234176 (The Pile)

Max Activating Token Index: 704

Text #14

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3333. Min Act: -0.0000

Data Index: 125523 (The Pile)

Max Activating Token Index: 406

Text #15

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3203. Min Act: -0.0000

Data Index: 610460 (The Pile)

Max Activating Token Index: 37

Text #16

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3264. Min Act: -0.0000

Data Index: 1433489 (The Pile)

Max Activating Token Index: 766

Text #17

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3678. Min Act: -0.0000

Data Index: 86461 (The Pile)

Max Activating Token Index: 252

Text #18

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3440. Min Act: -0.0000

Data Index: 1881485 (The Pile)

Max Activating Token Index: 291

Text #19

Max Range: 0.4130. Min Range: -0.4130

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1899870 (The Pile)

Max Activating Token Index: 54