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

Dataset: The Pile

Neuron 566 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2043. Min Range: -5.2043

Max Act: 5.2043. Min Act: -0.0000

Data Index: 197245 (The Pile)

Max Activating Token Index: 201

Text #1

Max Range: 5.2043. Min Range: -5.2043

Max Act: 4.6374. Min Act: -0.0000

Data Index: 862041 (The Pile)

Max Activating Token Index: 882

Text #2

Max Range: 5.2043. Min Range: -5.2043

Max Act: 4.5729. Min Act: -0.0000

Data Index: 1951183 (The Pile)

Max Activating Token Index: 978

Text #3

Max Range: 5.2043. Min Range: -5.2043

Max Act: 4.5879. Min Act: -0.0000

Data Index: 1425169 (The Pile)

Max Activating Token Index: 151

Text #4

Max Range: 5.2043. Min Range: -5.2043

Max Act: 4.1097. Min Act: -0.0000

Data Index: 309998 (The Pile)

Max Activating Token Index: 534

Text #5

Max Range: 5.2043. Min Range: -5.2043

Max Act: 3.9845. Min Act: -0.0000

Data Index: 1864664 (The Pile)

Max Activating Token Index: 363

Text #6

Max Range: 5.2043. Min Range: -5.2043

Max Act: 4.1490. Min Act: -0.0000

Data Index: 923962 (The Pile)

Max Activating Token Index: 446

Text #7

Max Range: 5.2043. Min Range: -5.2043

Max Act: 4.0722. Min Act: -0.0000

Data Index: 58244 (The Pile)

Max Activating Token Index: 659

Text #8

Max Range: 5.2043. Min Range: -5.2043

Max Act: 3.8967. Min Act: -0.0000

Data Index: 1317832 (The Pile)

Max Activating Token Index: 658

Text #9

Max Range: 5.2043. Min Range: -5.2043

Max Act: 3.4577. Min Act: -0.0000

Data Index: 1966714 (The Pile)

Max Activating Token Index: 690

Text #10

Max Range: 5.2043. Min Range: -5.2043

Max Act: 3.7671. Min Act: -0.0000

Data Index: 242756 (The Pile)

Max Activating Token Index: 964

Text #11

Max Range: 5.2043. Min Range: -5.2043

Max Act: 3.7852. Min Act: -0.0000

Data Index: 1350724 (The Pile)

Max Activating Token Index: 212

Text #12

Max Range: 5.2043. Min Range: -5.2043

Max Act: 4.0160. Min Act: -0.0000

Data Index: 226472 (The Pile)

Max Activating Token Index: 171

Text #13

Max Range: 5.2043. Min Range: -5.2043

Max Act: 3.4850. Min Act: -0.0000

Data Index: 2195 (The Pile)

Max Activating Token Index: 607

Text #14

Max Range: 5.2043. Min Range: -5.2043

Max Act: 3.6119. Min Act: -0.0000

Data Index: 1957152 (The Pile)

Max Activating Token Index: 751

Text #15

Max Range: 5.2043. Min Range: -5.2043

Max Act: 3.5542. Min Act: -0.0000

Data Index: 84205 (The Pile)

Max Activating Token Index: 973

Text #16

Max Range: 5.2043. Min Range: -5.2043

Max Act: 3.3526. Min Act: -0.0000

Data Index: 393843 (The Pile)

Max Activating Token Index: 209

Text #17

Max Range: 5.2043. Min Range: -5.2043

Max Act: 3.4830. Min Act: -0.0000

Data Index: 1191832 (The Pile)

Max Activating Token Index: 388

Text #18

Max Range: 5.2043. Min Range: -5.2043

Max Act: 3.6090. Min Act: -0.0000

Data Index: 1707117 (The Pile)

Max Activating Token Index: 724

Text #19

Max Range: 5.2043. Min Range: -5.2043

Max Act: 3.0161. Min Act: -0.0000

Data Index: 1694830 (The Pile)

Max Activating Token Index: 805