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

Dataset: The Pile

Neuron 1802 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: 0.9228. Min Range: -0.9228

Max Act: 0.9228. Min Act: -0.0000

Data Index: 1124475 (The Pile)

Max Activating Token Index: 655

Text #1

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1149767 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1125477 (The Pile)

Max Activating Token Index: 655

Text #3

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.7059. Min Act: -0.0000

Data Index: 1876821 (The Pile)

Max Activating Token Index: 201

Text #4

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.6822. Min Act: -0.0000

Data Index: 1465961 (The Pile)

Max Activating Token Index: 342

Text #5

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.7313. Min Act: -0.0000

Data Index: 268145 (The Pile)

Max Activating Token Index: 512

Text #6

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.8108. Min Act: -0.0000

Data Index: 467229 (The Pile)

Max Activating Token Index: 43

Text #7

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1775278 (The Pile)

Max Activating Token Index: 57

Text #8

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.7143. Min Act: -0.0000

Data Index: 191546 (The Pile)

Max Activating Token Index: 156

Text #9

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.6232. Min Act: -0.0000

Data Index: 550650 (The Pile)

Max Activating Token Index: 212

Text #10

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.6672. Min Act: -0.0000

Data Index: 593838 (The Pile)

Max Activating Token Index: 283

Text #11

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.6625. Min Act: -0.0000

Data Index: 1029979 (The Pile)

Max Activating Token Index: 441

Text #12

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.6133. Min Act: -0.0000

Data Index: 131665 (The Pile)

Max Activating Token Index: 791

Text #13

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1509558 (The Pile)

Max Activating Token Index: 102

Text #14

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.6646. Min Act: -0.0000

Data Index: 1139101 (The Pile)

Max Activating Token Index: 313

Text #15

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.5743. Min Act: -0.0000

Data Index: 1132634 (The Pile)

Max Activating Token Index: 968

Text #16

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.6052. Min Act: -0.0000

Data Index: 1980922 (The Pile)

Max Activating Token Index: 146

Text #17

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.6243. Min Act: -0.0000

Data Index: 550411 (The Pile)

Max Activating Token Index: 981

Text #18

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.6170. Min Act: -0.0000

Data Index: 1293349 (The Pile)

Max Activating Token Index: 790

Text #19

Max Range: 0.9228. Min Range: -0.9228

Max Act: 0.6085. Min Act: -0.0000

Data Index: 143455 (The Pile)

Max Activating Token Index: 714