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

Dataset: The Pile

Neuron 4700 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: 1.7283. Min Range: -1.7283

Max Act: 1.7283. Min Act: -0.0000

Data Index: 221395 (The Pile)

Max Activating Token Index: 57

Text #1

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.2812. Min Act: -0.0000

Data Index: 1482171 (The Pile)

Max Activating Token Index: 450

Text #2

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.2680. Min Act: -0.0000

Data Index: 899382 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.0933. Min Act: -0.0000

Data Index: 967994 (The Pile)

Max Activating Token Index: 314

Text #4

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.1338. Min Act: -0.0000

Data Index: 397815 (The Pile)

Max Activating Token Index: 39

Text #5

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.1347. Min Act: -0.0000

Data Index: 968685 (The Pile)

Max Activating Token Index: 218

Text #6

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.0665. Min Act: -0.0000

Data Index: 1268596 (The Pile)

Max Activating Token Index: 578

Text #7

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.0163. Min Act: -0.0000

Data Index: 351641 (The Pile)

Max Activating Token Index: 417

Text #8

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.0771. Min Act: 0.0000

Data Index: 1594677 (The Pile)

Max Activating Token Index: 532

Text #9

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.0039. Min Act: -0.0000

Data Index: 1929371 (The Pile)

Max Activating Token Index: 780

Text #10

Max Range: 1.7283. Min Range: -1.7283

Max Act: 0.9915. Min Act: -0.0000

Data Index: 1956154 (The Pile)

Max Activating Token Index: 175

Text #11

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.0332. Min Act: -0.0000

Data Index: 1097011 (The Pile)

Max Activating Token Index: 144

Text #12

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.0128. Min Act: -0.0000

Data Index: 426282 (The Pile)

Max Activating Token Index: 355

Text #13

Max Range: 1.7283. Min Range: -1.7283

Max Act: 0.9810. Min Act: -0.0000

Data Index: 1872427 (The Pile)

Max Activating Token Index: 516

Text #14

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.0495. Min Act: -0.0000

Data Index: 552402 (The Pile)

Max Activating Token Index: 491

Text #15

Max Range: 1.7283. Min Range: -1.7283

Max Act: 0.9440. Min Act: -0.0000

Data Index: 1758696 (The Pile)

Max Activating Token Index: 783

Text #16

Max Range: 1.7283. Min Range: -1.7283

Max Act: 0.9989. Min Act: -0.0000

Data Index: 329151 (The Pile)

Max Activating Token Index: 585

Text #17

Max Range: 1.7283. Min Range: -1.7283

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1152865 (The Pile)

Max Activating Token Index: 334

Text #18

Max Range: 1.7283. Min Range: -1.7283

Max Act: 0.8704. Min Act: 0.0001

Data Index: 877634 (The Pile)

Max Activating Token Index: 366

Text #19

Max Range: 1.7283. Min Range: -1.7283

Max Act: 0.9265. Min Act: 0.0000

Data Index: 917841 (The Pile)

Max Activating Token Index: 549