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

Dataset: The Pile

Neuron 3622 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: 0.1436. Min Range: -0.1436

Max Act: 0.1436. Min Act: -0.0000

Data Index: 450173 (The Pile)

Max Activating Token Index: 59

Text #1

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1224. Min Act: -0.0000

Data Index: 1293021 (The Pile)

Max Activating Token Index: 276

Text #2

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1000. Min Act: -0.0000

Data Index: 696946 (The Pile)

Max Activating Token Index: 222

Text #3

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0912. Min Act: -0.0000

Data Index: 219703 (The Pile)

Max Activating Token Index: 151

Text #4

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0892. Min Act: -0.0000

Data Index: 165779 (The Pile)

Max Activating Token Index: 253

Text #5

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0957. Min Act: -0.0000

Data Index: 1443419 (The Pile)

Max Activating Token Index: 123

Text #6

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1052. Min Act: -0.0000

Data Index: 1159704 (The Pile)

Max Activating Token Index: 177

Text #7

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0939. Min Act: -0.0000

Data Index: 1446772 (The Pile)

Max Activating Token Index: 260

Text #8

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0930. Min Act: -0.0000

Data Index: 1066350 (The Pile)

Max Activating Token Index: 39

Text #9

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0878. Min Act: -0.0000

Data Index: 1087641 (The Pile)

Max Activating Token Index: 163

Text #10

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0978. Min Act: -0.0000

Data Index: 172006 (The Pile)

Max Activating Token Index: 643

Text #11

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0670. Min Act: -0.0000

Data Index: 696404 (The Pile)

Max Activating Token Index: 766

Text #12

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0850. Min Act: -0.0000

Data Index: 683182 (The Pile)

Max Activating Token Index: 741

Text #13

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1887534 (The Pile)

Max Activating Token Index: 28

Text #14

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0800. Min Act: -0.0000

Data Index: 1584284 (The Pile)

Max Activating Token Index: 702

Text #15

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0797. Min Act: -0.0000

Data Index: 1450261 (The Pile)

Max Activating Token Index: 701

Text #16

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0841. Min Act: -0.0000

Data Index: 255334 (The Pile)

Max Activating Token Index: 551

Text #17

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0782. Min Act: -0.0000

Data Index: 1891169 (The Pile)

Max Activating Token Index: 742

Text #18

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0839. Min Act: -0.0000

Data Index: 372946 (The Pile)

Max Activating Token Index: 423

Text #19

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.0810. Min Act: -0.0000

Data Index: 1079583 (The Pile)

Max Activating Token Index: 78