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

Dataset: The Pile

Neuron 1202 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: 1.8160. Min Range: -1.8160

Max Act: 1.7449. Min Act: -0.0000

Data Index: 285192 (The Pile)

Max Activating Token Index: 963

Text #1

Max Range: 1.8160. Min Range: -1.8160

Max Act: 1.8160. Min Act: -0.0000

Data Index: 1485269 (The Pile)

Max Activating Token Index: 762

Text #2

Max Range: 1.8160. Min Range: -1.8160

Max Act: 1.6532. Min Act: -0.0000

Data Index: 1434084 (The Pile)

Max Activating Token Index: 1013

Text #3

Max Range: 1.8160. Min Range: -1.8160

Max Act: 1.6375. Min Act: -0.0000

Data Index: 800205 (The Pile)

Max Activating Token Index: 887

Text #4

Max Range: 1.8160. Min Range: -1.8160

Max Act: 1.6272. Min Act: -0.0000

Data Index: 1380847 (The Pile)

Max Activating Token Index: 671

Text #5

Max Range: 1.8160. Min Range: -1.8160

Max Act: 1.6596. Min Act: -0.0000

Data Index: 749422 (The Pile)

Max Activating Token Index: 611

Text #6

Max Range: 1.8160. Min Range: -1.8160

Max Act: 1.4676. Min Act: -0.0000

Data Index: 247377 (The Pile)

Max Activating Token Index: 986

Text #7

Max Range: 1.8160. Min Range: -1.8160

Max Act: 1.5960. Min Act: -0.0000

Data Index: 916997 (The Pile)

Max Activating Token Index: 721

Text #8

Max Range: 1.8160. Min Range: -1.8160

Max Act: 1.4587. Min Act: -0.0000

Data Index: 145963 (The Pile)

Max Activating Token Index: 842

Text #9

Max Range: 1.8160. Min Range: -1.8160

Max Act: 1.5113. Min Act: -0.0000

Data Index: 487624 (The Pile)

Max Activating Token Index: 472

Text #10

Max Range: 1.8160. Min Range: -1.8160

Max Act: 1.3877. Min Act: -0.0000

Data Index: 1482125 (The Pile)

Max Activating Token Index: 804

Text #11

Max Range: 1.8160. Min Range: -1.8160

Max Act: 1.4740. Min Act: -0.0000

Data Index: 1520240 (The Pile)

Max Activating Token Index: 546

Text #12

Max Range: 1.8160. Min Range: -1.8160

Max Act: 1.4623. Min Act: -0.0000

Data Index: 1455819 (The Pile)

Max Activating Token Index: 584

Text #13

Max Range: 1.8160. Min Range: -1.8160

Max Act: 1.3437. Min Act: -0.0000

Data Index: 270650 (The Pile)

Max Activating Token Index: 862

Text #14

Max Range: 1.8160. Min Range: -1.8160

Max Act: 1.4147. Min Act: -0.0000

Data Index: 1827842 (The Pile)

Max Activating Token Index: 636

Text #15

Max Range: 1.8160. Min Range: -1.8160

Max Act: 1.4068. Min Act: -0.0000

Data Index: 753828 (The Pile)

Max Activating Token Index: 285

Text #16

Max Range: 1.8160. Min Range: -1.8160

Max Act: 1.3225. Min Act: -0.0000

Data Index: 419419 (The Pile)

Max Activating Token Index: 83

Text #17

Max Range: 1.8160. Min Range: -1.8160

Max Act: 1.3877. Min Act: -0.0000

Data Index: 1630907 (The Pile)

Max Activating Token Index: 393

Text #18

Max Range: 1.8160. Min Range: -1.8160

Max Act: 1.2803. Min Act: -0.0000

Data Index: 1043613 (The Pile)

Max Activating Token Index: 913

Text #19

Max Range: 1.8160. Min Range: -1.8160

Max Act: 1.2899. Min Act: -0.0000

Data Index: 391808 (The Pile)

Max Activating Token Index: 877