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

Dataset: The Pile

Neuron 3891 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: 6.0854. Min Range: -6.0854

Max Act: 6.0854. Min Act: -0.0000

Data Index: 1090090 (The Pile)

Max Activating Token Index: 191

Text #1

Max Range: 6.0854. Min Range: -6.0854

Max Act: 5.2976. Min Act: -0.0000

Data Index: 1757044 (The Pile)

Max Activating Token Index: 238

Text #2

Max Range: 6.0854. Min Range: -6.0854

Max Act: 4.4162. Min Act: -0.0000

Data Index: 994367 (The Pile)

Max Activating Token Index: 42

Text #3

Max Range: 6.0854. Min Range: -6.0854

Max Act: 3.9159. Min Act: -0.0000

Data Index: 1535760 (The Pile)

Max Activating Token Index: 290

Text #4

Max Range: 6.0854. Min Range: -6.0854

Max Act: 3.9770. Min Act: -0.0000

Data Index: 1647902 (The Pile)

Max Activating Token Index: 98

Text #5

Max Range: 6.0854. Min Range: -6.0854

Max Act: 4.0802. Min Act: -0.0000

Data Index: 124709 (The Pile)

Max Activating Token Index: 1004

Text #6

Max Range: 6.0854. Min Range: -6.0854

Max Act: 4.2242. Min Act: -0.0000

Data Index: 873601 (The Pile)

Max Activating Token Index: 40

Text #7

Max Range: 6.0854. Min Range: -6.0854

Max Act: 3.3493. Min Act: -0.0000

Data Index: 1577416 (The Pile)

Max Activating Token Index: 100

Text #8

Max Range: 6.0854. Min Range: -6.0854

Max Act: 3.7965. Min Act: -0.0000

Data Index: 1430339 (The Pile)

Max Activating Token Index: 310

Text #9

Max Range: 6.0854. Min Range: -6.0854

Max Act: 2.9520. Min Act: -0.0000

Data Index: 1723172 (The Pile)

Max Activating Token Index: 1006

Text #10

Max Range: 6.0854. Min Range: -6.0854

Max Act: 3.8914. Min Act: -0.0000

Data Index: 351243 (The Pile)

Max Activating Token Index: 684

Text #11

Max Range: 6.0854. Min Range: -6.0854

Max Act: 3.3160. Min Act: -0.0000

Data Index: 363604 (The Pile)

Max Activating Token Index: 22

Text #12

Max Range: 6.0854. Min Range: -6.0854

Max Act: 3.0077. Min Act: -0.0000

Data Index: 385362 (The Pile)

Max Activating Token Index: 936

Text #13

Max Range: 6.0854. Min Range: -6.0854

Max Act: 3.5944. Min Act: -0.0000

Data Index: 886796 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 6.0854. Min Range: -6.0854

Max Act: 3.1569. Min Act: -0.0000

Data Index: 900669 (The Pile)

Max Activating Token Index: 887

Text #15

Max Range: 6.0854. Min Range: -6.0854

Max Act: 2.9300. Min Act: -0.0000

Data Index: 271097 (The Pile)

Max Activating Token Index: 743

Text #16

Max Range: 6.0854. Min Range: -6.0854

Max Act: 3.4295. Min Act: -0.0000

Data Index: 1749584 (The Pile)

Max Activating Token Index: 521

Text #17

Max Range: 6.0854. Min Range: -6.0854

Max Act: 3.7208. Min Act: -0.0000

Data Index: 1047485 (The Pile)

Max Activating Token Index: 486

Text #18

Max Range: 6.0854. Min Range: -6.0854

Max Act: 3.2506. Min Act: -0.0000

Data Index: 1461622 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 6.0854. Min Range: -6.0854

Max Act: 3.3767. Min Act: -0.0000

Data Index: 1106170 (The Pile)

Max Activating Token Index: 102