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

Dataset: The Pile

Neuron 3244 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.8019. Min Act: -0.0000

Data Index: 336510 (The Pile)

Max Activating Token Index: 221

Text #1

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1887278 (The Pile)

Max Activating Token Index: 446

Text #2

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.7047. Min Act: -0.0000

Data Index: 1209224 (The Pile)

Max Activating Token Index: 477

Text #3

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.7368. Min Act: -0.0000

Data Index: 1228408 (The Pile)

Max Activating Token Index: 139

Text #4

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.4971. Min Act: -0.0000

Data Index: 901941 (The Pile)

Max Activating Token Index: 683

Text #5

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1523516 (The Pile)

Max Activating Token Index: 88

Text #6

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1497091 (The Pile)

Max Activating Token Index: 95

Text #7

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1599758 (The Pile)

Max Activating Token Index: 294

Text #8

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1382516 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.5806. Min Act: -0.0000

Data Index: 1274306 (The Pile)

Max Activating Token Index: 699

Text #10

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1685894 (The Pile)

Max Activating Token Index: 420

Text #11

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.5761. Min Act: -0.0000

Data Index: 663494 (The Pile)

Max Activating Token Index: 699

Text #12

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.6731. Min Act: -0.0000

Data Index: 186477 (The Pile)

Max Activating Token Index: 578

Text #13

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.5980. Min Act: -0.0000

Data Index: 725295 (The Pile)

Max Activating Token Index: 234

Text #14

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.5163. Min Act: -0.0000

Data Index: 100808 (The Pile)

Max Activating Token Index: 155

Text #15

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.6105. Min Act: -0.0000

Data Index: 1203256 (The Pile)

Max Activating Token Index: 182

Text #16

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.5566. Min Act: -0.0000

Data Index: 80018 (The Pile)

Max Activating Token Index: 447

Text #17

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.6183. Min Act: -0.0000

Data Index: 82111 (The Pile)

Max Activating Token Index: 176

Text #18

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.5479. Min Act: -0.0000

Data Index: 1594914 (The Pile)

Max Activating Token Index: 516

Text #19

Max Range: 0.8019. Min Range: -0.8019

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1006389 (The Pile)

Max Activating Token Index: 796