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

Dataset: The Pile

Neuron 507 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: 5.2030. Min Range: -5.2030

Max Act: 4.8945. Min Act: -0.0000

Data Index: 1018102 (The Pile)

Max Activating Token Index: 710

Text #1

Max Range: 5.2030. Min Range: -5.2030

Max Act: 5.2030. Min Act: -0.0000

Data Index: 896054 (The Pile)

Max Activating Token Index: 511

Text #2

Max Range: 5.2030. Min Range: -5.2030

Max Act: 4.6678. Min Act: -0.0000

Data Index: 1375762 (The Pile)

Max Activating Token Index: 160

Text #3

Max Range: 5.2030. Min Range: -5.2030

Max Act: 4.1596. Min Act: -0.0000

Data Index: 485804 (The Pile)

Max Activating Token Index: 130

Text #4

Max Range: 5.2030. Min Range: -5.2030

Max Act: 4.0703. Min Act: -0.0000

Data Index: 101609 (The Pile)

Max Activating Token Index: 399

Text #5

Max Range: 5.2030. Min Range: -5.2030

Max Act: 4.0140. Min Act: -0.0000

Data Index: 1084452 (The Pile)

Max Activating Token Index: 800

Text #6

Max Range: 5.2030. Min Range: -5.2030

Max Act: 4.2224. Min Act: -0.0000

Data Index: 452326 (The Pile)

Max Activating Token Index: 121

Text #7

Max Range: 5.2030. Min Range: -5.2030

Max Act: 4.0149. Min Act: -0.0000

Data Index: 1866495 (The Pile)

Max Activating Token Index: 294

Text #8

Max Range: 5.2030. Min Range: -5.2030

Max Act: 3.5626. Min Act: -0.0000

Data Index: 1951519 (The Pile)

Max Activating Token Index: 385

Text #9

Max Range: 5.2030. Min Range: -5.2030

Max Act: 3.8235. Min Act: -0.0000

Data Index: 1235044 (The Pile)

Max Activating Token Index: 217

Text #10

Max Range: 5.2030. Min Range: -5.2030

Max Act: 3.8535. Min Act: -0.0000

Data Index: 1264311 (The Pile)

Max Activating Token Index: 854

Text #11

Max Range: 5.2030. Min Range: -5.2030

Max Act: 3.6520. Min Act: -0.0000

Data Index: 222675 (The Pile)

Max Activating Token Index: 251

Text #12

Max Range: 5.2030. Min Range: -5.2030

Max Act: 3.7147. Min Act: -0.0000

Data Index: 1713120 (The Pile)

Max Activating Token Index: 136

Text #13

Max Range: 5.2030. Min Range: -5.2030

Max Act: 3.6726. Min Act: -0.0000

Data Index: 1445062 (The Pile)

Max Activating Token Index: 197

Text #14

Max Range: 5.2030. Min Range: -5.2030

Max Act: 3.7578. Min Act: -0.0000

Data Index: 604585 (The Pile)

Max Activating Token Index: 776

Text #15

Max Range: 5.2030. Min Range: -5.2030

Max Act: 3.7078. Min Act: -0.0000

Data Index: 106084 (The Pile)

Max Activating Token Index: 716

Text #16

Max Range: 5.2030. Min Range: -5.2030

Max Act: 3.7795. Min Act: -0.0000

Data Index: 689233 (The Pile)

Max Activating Token Index: 829

Text #17

Max Range: 5.2030. Min Range: -5.2030

Max Act: 3.4154. Min Act: -0.0000

Data Index: 1633779 (The Pile)

Max Activating Token Index: 331

Text #18

Max Range: 5.2030. Min Range: -5.2030

Max Act: 3.4303. Min Act: -0.0000

Data Index: 795813 (The Pile)

Max Activating Token Index: 883

Text #19

Max Range: 5.2030. Min Range: -5.2030

Max Act: 3.5353. Min Act: -0.0000

Data Index: 1497627 (The Pile)

Max Activating Token Index: 367