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

Dataset: The Pile

Neuron 1858 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.8941. Min Range: -1.8941

Max Act: 1.8941. Min Act: -0.0000

Data Index: 1696419 (The Pile)

Max Activating Token Index: 605

Text #1

Max Range: 1.8941. Min Range: -1.8941

Max Act: 1.4940. Min Act: -0.0000

Data Index: 1792353 (The Pile)

Max Activating Token Index: 842

Text #2

Max Range: 1.8941. Min Range: -1.8941

Max Act: 1.6754. Min Act: -0.0000

Data Index: 733007 (The Pile)

Max Activating Token Index: 632

Text #3

Max Range: 1.8941. Min Range: -1.8941

Max Act: 1.4404. Min Act: -0.0000

Data Index: 34658 (The Pile)

Max Activating Token Index: 710

Text #4

Max Range: 1.8941. Min Range: -1.8941

Max Act: 1.3477. Min Act: -0.0000

Data Index: 1286363 (The Pile)

Max Activating Token Index: 848

Text #5

Max Range: 1.8941. Min Range: -1.8941

Max Act: 1.3023. Min Act: -0.0000

Data Index: 1662392 (The Pile)

Max Activating Token Index: 662

Text #6

Max Range: 1.8941. Min Range: -1.8941

Max Act: 1.3198. Min Act: -0.0000

Data Index: 1962254 (The Pile)

Max Activating Token Index: 1004

Text #7

Max Range: 1.8941. Min Range: -1.8941

Max Act: 1.2649. Min Act: -0.0000

Data Index: 1117923 (The Pile)

Max Activating Token Index: 993

Text #8

Max Range: 1.8941. Min Range: -1.8941

Max Act: 1.2964. Min Act: -0.0000

Data Index: 669704 (The Pile)

Max Activating Token Index: 378

Text #9

Max Range: 1.8941. Min Range: -1.8941

Max Act: 1.3248. Min Act: -0.0000

Data Index: 500958 (The Pile)

Max Activating Token Index: 360

Text #10

Max Range: 1.8941. Min Range: -1.8941

Max Act: 1.1744. Min Act: -0.0000

Data Index: 1139136 (The Pile)

Max Activating Token Index: 975

Text #11

Max Range: 1.8941. Min Range: -1.8941

Max Act: 1.2694. Min Act: -0.0000

Data Index: 705020 (The Pile)

Max Activating Token Index: 845

Text #12

Max Range: 1.8941. Min Range: -1.8941

Max Act: 1.1929. Min Act: -0.0000

Data Index: 1859748 (The Pile)

Max Activating Token Index: 313

Text #13

Max Range: 1.8941. Min Range: -1.8941

Max Act: 1.1724. Min Act: -0.0000

Data Index: 1422914 (The Pile)

Max Activating Token Index: 848

Text #14

Max Range: 1.8941. Min Range: -1.8941

Max Act: 1.2582. Min Act: -0.0000

Data Index: 504620 (The Pile)

Max Activating Token Index: 500

Text #15

Max Range: 1.8941. Min Range: -1.8941

Max Act: 1.2845. Min Act: -0.0000

Data Index: 1230317 (The Pile)

Max Activating Token Index: 378

Text #16

Max Range: 1.8941. Min Range: -1.8941

Max Act: 1.2892. Min Act: -0.0000

Data Index: 1287412 (The Pile)

Max Activating Token Index: 681

Text #17

Max Range: 1.8941. Min Range: -1.8941

Max Act: 1.3126. Min Act: -0.0000

Data Index: 1010648 (The Pile)

Max Activating Token Index: 375

Text #18

Max Range: 1.8941. Min Range: -1.8941

Max Act: 1.2379. Min Act: -0.0000

Data Index: 1126609 (The Pile)

Max Activating Token Index: 237

Text #19

Max Range: 1.8941. Min Range: -1.8941

Max Act: 1.2387. Min Act: -0.0000

Data Index: 1996602 (The Pile)

Max Activating Token Index: 72