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

Dataset: The Pile

Neuron 2820 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: 1.6078. Min Range: -1.6078

Max Act: 1.5286. Min Act: -0.0000

Data Index: 377228 (The Pile)

Max Activating Token Index: 571

Text #1

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.6078. Min Act: -0.0000

Data Index: 1010343 (The Pile)

Max Activating Token Index: 588

Text #2

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.3077. Min Act: -0.0000

Data Index: 718853 (The Pile)

Max Activating Token Index: 424

Text #3

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.1113. Min Act: -0.0000

Data Index: 811478 (The Pile)

Max Activating Token Index: 450

Text #4

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.1827. Min Act: -0.0000

Data Index: 1645860 (The Pile)

Max Activating Token Index: 748

Text #5

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.0301. Min Act: -0.0000

Data Index: 199128 (The Pile)

Max Activating Token Index: 329

Text #6

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.0136. Min Act: -0.0000

Data Index: 1224347 (The Pile)

Max Activating Token Index: 315

Text #7

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.1721. Min Act: -0.0000

Data Index: 1062555 (The Pile)

Max Activating Token Index: 657

Text #8

Max Range: 1.6078. Min Range: -1.6078

Max Act: 0.9478. Min Act: -0.0000

Data Index: 160277 (The Pile)

Max Activating Token Index: 890

Text #9

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.0446. Min Act: -0.0000

Data Index: 356857 (The Pile)

Max Activating Token Index: 560

Text #10

Max Range: 1.6078. Min Range: -1.6078

Max Act: 0.9381. Min Act: -0.0000

Data Index: 537792 (The Pile)

Max Activating Token Index: 714

Text #11

Max Range: 1.6078. Min Range: -1.6078

Max Act: 0.9404. Min Act: -0.0000

Data Index: 415023 (The Pile)

Max Activating Token Index: 71

Text #12

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.0950. Min Act: -0.0000

Data Index: 660809 (The Pile)

Max Activating Token Index: 987

Text #13

Max Range: 1.6078. Min Range: -1.6078

Max Act: 0.9532. Min Act: -0.0000

Data Index: 1657004 (The Pile)

Max Activating Token Index: 201

Text #14

Max Range: 1.6078. Min Range: -1.6078

Max Act: 0.8743. Min Act: -0.0000

Data Index: 1208042 (The Pile)

Max Activating Token Index: 212

Text #15

Max Range: 1.6078. Min Range: -1.6078

Max Act: 0.8283. Min Act: -0.0000

Data Index: 852088 (The Pile)

Max Activating Token Index: 424

Text #16

Max Range: 1.6078. Min Range: -1.6078

Max Act: 0.7243. Min Act: -0.0000

Data Index: 311040 (The Pile)

Max Activating Token Index: 917

Text #17

Max Range: 1.6078. Min Range: -1.6078

Max Act: 0.6582. Min Act: -0.0000

Data Index: 687072 (The Pile)

Max Activating Token Index: 692

Text #18

Max Range: 1.6078. Min Range: -1.6078

Max Act: 0.6250. Min Act: -0.0000

Data Index: 165666 (The Pile)

Max Activating Token Index: 169

Text #19

Max Range: 1.6078. Min Range: -1.6078

Max Act: 0.6080. Min Act: -0.0000

Data Index: 203532 (The Pile)

Max Activating Token Index: 18