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

Dataset: The Pile

Neuron 4831 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: 0.6403. Min Range: -0.6403

Max Act: 0.6403. Min Act: -0.0000

Data Index: 100140 (The Pile)

Max Activating Token Index: 650

Text #1

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.6146. Min Act: -0.0000

Data Index: 622362 (The Pile)

Max Activating Token Index: 208

Text #2

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5996. Min Act: -0.0000

Data Index: 298995 (The Pile)

Max Activating Token Index: 264

Text #3

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5552. Min Act: -0.0000

Data Index: 785691 (The Pile)

Max Activating Token Index: 271

Text #4

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5836. Min Act: -0.0000

Data Index: 513529 (The Pile)

Max Activating Token Index: 19

Text #5

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5809. Min Act: -0.0000

Data Index: 1779742 (The Pile)

Max Activating Token Index: 839

Text #6

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1152839 (The Pile)

Max Activating Token Index: 770

Text #7

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5590. Min Act: -0.0000

Data Index: 199536 (The Pile)

Max Activating Token Index: 768

Text #8

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1751778 (The Pile)

Max Activating Token Index: 36

Text #9

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1897513 (The Pile)

Max Activating Token Index: 108

Text #10

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5621. Min Act: -0.0000

Data Index: 165739 (The Pile)

Max Activating Token Index: 225

Text #11

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5289. Min Act: -0.0000

Data Index: 1281084 (The Pile)

Max Activating Token Index: 603

Text #12

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5129. Min Act: -0.0000

Data Index: 187236 (The Pile)

Max Activating Token Index: 263

Text #13

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5469. Min Act: -0.0000

Data Index: 1329355 (The Pile)

Max Activating Token Index: 536

Text #14

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5422. Min Act: -0.0000

Data Index: 974618 (The Pile)

Max Activating Token Index: 422

Text #15

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5414. Min Act: -0.0000

Data Index: 86388 (The Pile)

Max Activating Token Index: 113

Text #16

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5048. Min Act: -0.0000

Data Index: 1612679 (The Pile)

Max Activating Token Index: 600

Text #17

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1757800 (The Pile)

Max Activating Token Index: 354

Text #18

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5238. Min Act: -0.0000

Data Index: 942531 (The Pile)

Max Activating Token Index: 487

Text #19

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4963. Min Act: -0.0000

Data Index: 1073756 (The Pile)

Max Activating Token Index: 238