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

Dataset: The Pile

Neuron 3159 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: 0.8254. Min Range: -0.8254

Max Act: 0.8222. Min Act: -0.0000

Data Index: 151438 (The Pile)

Max Activating Token Index: 241

Text #1

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.7984. Min Act: -0.0000

Data Index: 1361024 (The Pile)

Max Activating Token Index: 665

Text #2

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.8254. Min Act: -0.0000

Data Index: 1402083 (The Pile)

Max Activating Token Index: 106

Text #3

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.7411. Min Act: -0.0000

Data Index: 1378591 (The Pile)

Max Activating Token Index: 507

Text #4

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.7618. Min Act: -0.0000

Data Index: 696417 (The Pile)

Max Activating Token Index: 724

Text #5

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.6922. Min Act: -0.0000

Data Index: 42678 (The Pile)

Max Activating Token Index: 658

Text #6

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.7298. Min Act: -0.0000

Data Index: 26945 (The Pile)

Max Activating Token Index: 546

Text #7

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.7151. Min Act: -0.0000

Data Index: 25078 (The Pile)

Max Activating Token Index: 126

Text #8

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.6573. Min Act: -0.0000

Data Index: 1856767 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.5922. Min Act: -0.0000

Data Index: 1861447 (The Pile)

Max Activating Token Index: 961

Text #10

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.6424. Min Act: -0.0000

Data Index: 1949751 (The Pile)

Max Activating Token Index: 251

Text #11

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.6641. Min Act: -0.0000

Data Index: 151589 (The Pile)

Max Activating Token Index: 206

Text #12

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.6296. Min Act: -0.0000

Data Index: 1068526 (The Pile)

Max Activating Token Index: 108

Text #13

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.6435. Min Act: -0.0000

Data Index: 1835809 (The Pile)

Max Activating Token Index: 695

Text #14

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.6296. Min Act: -0.0000

Data Index: 98156 (The Pile)

Max Activating Token Index: 930

Text #15

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.5781. Min Act: -0.0000

Data Index: 1982656 (The Pile)

Max Activating Token Index: 748

Text #16

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.5972. Min Act: -0.0000

Data Index: 1498309 (The Pile)

Max Activating Token Index: 421

Text #17

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1807663 (The Pile)

Max Activating Token Index: 207

Text #18

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1759910 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.5982. Min Act: -0.0000

Data Index: 811666 (The Pile)

Max Activating Token Index: 28