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

Dataset: The Pile

Neuron 943 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.3411. Min Act: -0.0000

Data Index: 469337 (The Pile)

Max Activating Token Index: 1010

Text #1

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.7936. Min Act: 0.0000

Data Index: 1441798 (The Pile)

Max Activating Token Index: 989

Text #2

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.8670. Min Act: -0.0000

Data Index: 150895 (The Pile)

Max Activating Token Index: 173

Text #3

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.9477. Min Act: -0.0000

Data Index: 635551 (The Pile)

Max Activating Token Index: 897

Text #4

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.8142. Min Act: -0.0000

Data Index: 613461 (The Pile)

Max Activating Token Index: 993

Text #5

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.8638. Min Act: 0.0000

Data Index: 992063 (The Pile)

Max Activating Token Index: 153

Text #6

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.7760. Min Act: -0.0000

Data Index: 350304 (The Pile)

Max Activating Token Index: 164

Text #7

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.8053. Min Act: -0.0000

Data Index: 394952 (The Pile)

Max Activating Token Index: 441

Text #8

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.7754. Min Act: -0.0000

Data Index: 1546290 (The Pile)

Max Activating Token Index: 618

Text #9

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.7383. Min Act: -0.0000

Data Index: 730772 (The Pile)

Max Activating Token Index: 637

Text #10

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.7784. Min Act: -0.0000

Data Index: 402837 (The Pile)

Max Activating Token Index: 165

Text #11

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.7765. Min Act: -0.0000

Data Index: 1843468 (The Pile)

Max Activating Token Index: 995

Text #12

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.6848. Min Act: -0.0000

Data Index: 1665304 (The Pile)

Max Activating Token Index: 305

Text #13

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.7176. Min Act: -0.0000

Data Index: 706390 (The Pile)

Max Activating Token Index: 551

Text #14

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.7621. Min Act: -0.0000

Data Index: 744450 (The Pile)

Max Activating Token Index: 193

Text #15

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.7136. Min Act: -0.0000

Data Index: 1081455 (The Pile)

Max Activating Token Index: 281

Text #16

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.7091. Min Act: 0.0000

Data Index: 324879 (The Pile)

Max Activating Token Index: 680

Text #17

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1261914 (The Pile)

Max Activating Token Index: 1009

Text #18

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.6984. Min Act: -0.0000

Data Index: 1828953 (The Pile)

Max Activating Token Index: 219

Text #19

Max Range: 1.3411. Min Range: -1.3411

Max Act: 0.7448. Min Act: -0.0000

Data Index: 3137 (The Pile)

Max Activating Token Index: 411