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

Dataset: The Pile

Neuron 4716 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: 5.3202. Min Range: -5.3202

Max Act: 3.6133. Min Act: -0.0000

Data Index: 1340542 (The Pile)

Max Activating Token Index: 954

Text #1

Max Range: 5.3202. Min Range: -5.3202

Max Act: 5.2663. Min Act: -0.0000

Data Index: 1522447 (The Pile)

Max Activating Token Index: 719

Text #2

Max Range: 5.3202. Min Range: -5.3202

Max Act: 5.3202. Min Act: -0.0000

Data Index: 1593965 (The Pile)

Max Activating Token Index: 777

Text #3

Max Range: 5.3202. Min Range: -5.3202

Max Act: 5.0116. Min Act: -0.0000

Data Index: 87966 (The Pile)

Max Activating Token Index: 859

Text #4

Max Range: 5.3202. Min Range: -5.3202

Max Act: 4.4935. Min Act: -0.0000

Data Index: 1289545 (The Pile)

Max Activating Token Index: 537

Text #5

Max Range: 5.3202. Min Range: -5.3202

Max Act: 4.1987. Min Act: -0.0000

Data Index: 617097 (The Pile)

Max Activating Token Index: 637

Text #6

Max Range: 5.3202. Min Range: -5.3202

Max Act: 4.4351. Min Act: -0.0000

Data Index: 1266756 (The Pile)

Max Activating Token Index: 229

Text #7

Max Range: 5.3202. Min Range: -5.3202

Max Act: 3.7545. Min Act: -0.0000

Data Index: 102356 (The Pile)

Max Activating Token Index: 259

Text #8

Max Range: 5.3202. Min Range: -5.3202

Max Act: 3.7409. Min Act: -0.0000

Data Index: 616668 (The Pile)

Max Activating Token Index: 173

Text #9

Max Range: 5.3202. Min Range: -5.3202

Max Act: 4.0092. Min Act: -0.0000

Data Index: 1882304 (The Pile)

Max Activating Token Index: 1022

Text #10

Max Range: 5.3202. Min Range: -5.3202

Max Act: 3.5092. Min Act: -0.0000

Data Index: 665521 (The Pile)

Max Activating Token Index: 688

Text #11

Max Range: 5.3202. Min Range: -5.3202

Max Act: 3.7837. Min Act: -0.0000

Data Index: 1438420 (The Pile)

Max Activating Token Index: 319

Text #12

Max Range: 5.3202. Min Range: -5.3202

Max Act: 4.4686. Min Act: -0.0000

Data Index: 1002295 (The Pile)

Max Activating Token Index: 813

Text #13

Max Range: 5.3202. Min Range: -5.3202

Max Act: 3.7832. Min Act: -0.0000

Data Index: 713197 (The Pile)

Max Activating Token Index: 763

Text #14

Max Range: 5.3202. Min Range: -5.3202

Max Act: 3.7378. Min Act: -0.0000

Data Index: 1795906 (The Pile)

Max Activating Token Index: 83

Text #15

Max Range: 5.3202. Min Range: -5.3202

Max Act: 4.0596. Min Act: -0.0000

Data Index: 254561 (The Pile)

Max Activating Token Index: 147

Text #16

Max Range: 5.3202. Min Range: -5.3202

Max Act: 3.4448. Min Act: -0.0000

Data Index: 1647213 (The Pile)

Max Activating Token Index: 465

Text #17

Max Range: 5.3202. Min Range: -5.3202

Max Act: 3.7400. Min Act: -0.0000

Data Index: 1727591 (The Pile)

Max Activating Token Index: 401

Text #18

Max Range: 5.3202. Min Range: -5.3202

Max Act: 3.9268. Min Act: -0.0000

Data Index: 1483313 (The Pile)

Max Activating Token Index: 850

Text #19

Max Range: 5.3202. Min Range: -5.3202

Max Act: 3.6879. Min Act: -0.0000

Data Index: 45361 (The Pile)

Max Activating Token Index: 627