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

Dataset: The Pile

Neuron 1584 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: 1.8241. Min Range: -1.8241

Max Act: 1.8241. Min Act: -0.0000

Data Index: 1429640 (The Pile)

Max Activating Token Index: 699

Text #1

Max Range: 1.8241. Min Range: -1.8241

Max Act: 1.7287. Min Act: -0.0000

Data Index: 1023011 (The Pile)

Max Activating Token Index: 551

Text #2

Max Range: 1.8241. Min Range: -1.8241

Max Act: 1.7853. Min Act: -0.0000

Data Index: 1294713 (The Pile)

Max Activating Token Index: 963

Text #3

Max Range: 1.8241. Min Range: -1.8241

Max Act: 1.5434. Min Act: -0.0000

Data Index: 43069 (The Pile)

Max Activating Token Index: 1021

Text #4

Max Range: 1.8241. Min Range: -1.8241

Max Act: 1.6169. Min Act: -0.0000

Data Index: 1150830 (The Pile)

Max Activating Token Index: 416

Text #5

Max Range: 1.8241. Min Range: -1.8241

Max Act: 1.5959. Min Act: -0.0000

Data Index: 542863 (The Pile)

Max Activating Token Index: 792

Text #6

Max Range: 1.8241. Min Range: -1.8241

Max Act: 1.5427. Min Act: -0.0000

Data Index: 892565 (The Pile)

Max Activating Token Index: 431

Text #7

Max Range: 1.8241. Min Range: -1.8241

Max Act: 1.5333. Min Act: -0.0000

Data Index: 633407 (The Pile)

Max Activating Token Index: 10

Text #8

Max Range: 1.8241. Min Range: -1.8241

Max Act: 1.4086. Min Act: -0.0000

Data Index: 298510 (The Pile)

Max Activating Token Index: 247

Text #9

Max Range: 1.8241. Min Range: -1.8241

Max Act: 1.4930. Min Act: -0.0000

Data Index: 1881639 (The Pile)

Max Activating Token Index: 152

Text #10

Max Range: 1.8241. Min Range: -1.8241

Max Act: 1.4829. Min Act: -0.0000

Data Index: 469170 (The Pile)

Max Activating Token Index: 871

Text #11

Max Range: 1.8241. Min Range: -1.8241

Max Act: 1.4273. Min Act: -0.0000

Data Index: 1368425 (The Pile)

Max Activating Token Index: 1015

Text #12

Max Range: 1.8241. Min Range: -1.8241

Max Act: 1.3848. Min Act: -0.0000

Data Index: 801229 (The Pile)

Max Activating Token Index: 869

Text #13

Max Range: 1.8241. Min Range: -1.8241

Max Act: 1.3733. Min Act: -0.0000

Data Index: 1094430 (The Pile)

Max Activating Token Index: 738

Text #14

Max Range: 1.8241. Min Range: -1.8241

Max Act: 1.3715. Min Act: -0.0000

Data Index: 1780763 (The Pile)

Max Activating Token Index: 498

Text #15

Max Range: 1.8241. Min Range: -1.8241

Max Act: 1.3623. Min Act: -0.0000

Data Index: 606552 (The Pile)

Max Activating Token Index: 142

Text #16

Max Range: 1.8241. Min Range: -1.8241

Max Act: 1.3375. Min Act: -0.0000

Data Index: 132788 (The Pile)

Max Activating Token Index: 857

Text #17

Max Range: 1.8241. Min Range: -1.8241

Max Act: 1.3184. Min Act: -0.0000

Data Index: 956256 (The Pile)

Max Activating Token Index: 593

Text #18

Max Range: 1.8241. Min Range: -1.8241

Max Act: 1.3265. Min Act: -0.0000

Data Index: 1652127 (The Pile)

Max Activating Token Index: 790

Text #19

Max Range: 1.8241. Min Range: -1.8241

Max Act: 1.2367. Min Act: -0.0000

Data Index: 1238987 (The Pile)

Max Activating Token Index: 661