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

Dataset: The Pile

Neuron 3421 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.3953. Min Act: -0.0000

Data Index: 194246 (The Pile)

Max Activating Token Index: 1017

Text #1

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.4431. Min Act: -0.0000

Data Index: 1186085 (The Pile)

Max Activating Token Index: 845

Text #2

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.3961. Min Act: -0.0000

Data Index: 1279762 (The Pile)

Max Activating Token Index: 431

Text #3

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.3185. Min Act: -0.0000

Data Index: 885712 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.2031. Min Act: -0.0000

Data Index: 7640 (The Pile)

Max Activating Token Index: 119

Text #5

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.0694. Min Act: -0.0000

Data Index: 604161 (The Pile)

Max Activating Token Index: 226

Text #6

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.0795. Min Act: -0.0000

Data Index: 780999 (The Pile)

Max Activating Token Index: 126

Text #7

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.2113. Min Act: -0.0000

Data Index: 520044 (The Pile)

Max Activating Token Index: 74

Text #8

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.1001. Min Act: -0.0000

Data Index: 322166 (The Pile)

Max Activating Token Index: 389

Text #9

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.0672. Min Act: -0.0000

Data Index: 391404 (The Pile)

Max Activating Token Index: 624

Text #10

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.0339. Min Act: -0.0000

Data Index: 236858 (The Pile)

Max Activating Token Index: 808

Text #11

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.9810. Min Act: -0.0000

Data Index: 1700104 (The Pile)

Max Activating Token Index: 848

Text #12

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.9419. Min Act: -0.0000

Data Index: 1013652 (The Pile)

Max Activating Token Index: 865

Text #13

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.8811. Min Act: -0.0000

Data Index: 1362016 (The Pile)

Max Activating Token Index: 896

Text #14

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1835611 (The Pile)

Max Activating Token Index: 868

Text #15

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.9092. Min Act: -0.0000

Data Index: 905616 (The Pile)

Max Activating Token Index: 404

Text #16

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.9051. Min Act: -0.0000

Data Index: 1651761 (The Pile)

Max Activating Token Index: 273

Text #17

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.9597. Min Act: -0.0000

Data Index: 975812 (The Pile)

Max Activating Token Index: 412

Text #18

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.8542. Min Act: -0.0000

Data Index: 1323815 (The Pile)

Max Activating Token Index: 155

Text #19

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.8823. Min Act: -0.0000

Data Index: 1878397 (The Pile)

Max Activating Token Index: 847