Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2198 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.5758. Min Act: -0.0000

Data Index: 1796035 (The Pile)

Max Activating Token Index: 31

Text #1

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.6002. Min Act: -0.0000

Data Index: 1100181 (The Pile)

Max Activating Token Index: 935

Text #2

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.5918. Min Act: -0.0000

Data Index: 1301831 (The Pile)

Max Activating Token Index: 39

Text #3

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.4177. Min Act: -0.0000

Data Index: 1034582 (The Pile)

Max Activating Token Index: 934

Text #4

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.4741. Min Act: -0.0000

Data Index: 1539754 (The Pile)

Max Activating Token Index: 672

Text #5

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.4146. Min Act: -0.0000

Data Index: 845224 (The Pile)

Max Activating Token Index: 944

Text #6

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.3654. Min Act: -0.0000

Data Index: 1245740 (The Pile)

Max Activating Token Index: 775

Text #7

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.3032. Min Act: -0.0000

Data Index: 1601798 (The Pile)

Max Activating Token Index: 85

Text #8

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.2102. Min Act: -0.0000

Data Index: 1242485 (The Pile)

Max Activating Token Index: 564

Text #9

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.2527. Min Act: -0.0000

Data Index: 888835 (The Pile)

Max Activating Token Index: 503

Text #10

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.2174. Min Act: -0.0000

Data Index: 122026 (The Pile)

Max Activating Token Index: 1018

Text #11

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.1133. Min Act: -0.0000

Data Index: 922958 (The Pile)

Max Activating Token Index: 422

Text #12

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.0828. Min Act: -0.0000

Data Index: 1834862 (The Pile)

Max Activating Token Index: 846

Text #13

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.1179. Min Act: -0.0000

Data Index: 1345337 (The Pile)

Max Activating Token Index: 566

Text #14

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.1100. Min Act: -0.0000

Data Index: 1836132 (The Pile)

Max Activating Token Index: 175

Text #15

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.0932. Min Act: -0.0000

Data Index: 1871201 (The Pile)

Max Activating Token Index: 413

Text #16

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.1371. Min Act: -0.0000

Data Index: 665058 (The Pile)

Max Activating Token Index: 665

Text #17

Max Range: 1.6002. Min Range: -1.6002

Max Act: 0.9944. Min Act: -0.0000

Data Index: 1658455 (The Pile)

Max Activating Token Index: 138

Text #18

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.0733. Min Act: -0.0000

Data Index: 583868 (The Pile)

Max Activating Token Index: 303

Text #19

Max Range: 1.6002. Min Range: -1.6002

Max Act: 1.0435. Min Act: -0.0000

Data Index: 1873682 (The Pile)

Max Activating Token Index: 164