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

Dataset: The Pile

Neuron 3130 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: 0.6552. Min Range: -0.6552

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1528022 (The Pile)

Max Activating Token Index: 247

Text #1

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.6360. Min Act: -0.0000

Data Index: 606658 (The Pile)

Max Activating Token Index: 994

Text #2

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5809. Min Act: -0.0000

Data Index: 1366033 (The Pile)

Max Activating Token Index: 727

Text #3

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.6552. Min Act: -0.0000

Data Index: 740342 (The Pile)

Max Activating Token Index: 819

Text #4

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5771. Min Act: -0.0000

Data Index: 1723429 (The Pile)

Max Activating Token Index: 942

Text #5

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1541461 (The Pile)

Max Activating Token Index: 412

Text #6

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1978726 (The Pile)

Max Activating Token Index: 941

Text #7

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5809. Min Act: -0.0000

Data Index: 1539418 (The Pile)

Max Activating Token Index: 50

Text #8

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5604. Min Act: -0.0000

Data Index: 857978 (The Pile)

Max Activating Token Index: 6

Text #9

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1154918 (The Pile)

Max Activating Token Index: 788

Text #10

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5436. Min Act: -0.0000

Data Index: 856499 (The Pile)

Max Activating Token Index: 202

Text #11

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5302. Min Act: -0.0000

Data Index: 517506 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1158202 (The Pile)

Max Activating Token Index: 300

Text #13

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5216. Min Act: -0.0000

Data Index: 1782333 (The Pile)

Max Activating Token Index: 96

Text #14

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1795635 (The Pile)

Max Activating Token Index: 5

Text #15

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5205. Min Act: -0.0000

Data Index: 18804 (The Pile)

Max Activating Token Index: 613

Text #16

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5300. Min Act: -0.0000

Data Index: 817763 (The Pile)

Max Activating Token Index: 573

Text #17

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5592. Min Act: -0.0000

Data Index: 1936487 (The Pile)

Max Activating Token Index: 381

Text #18

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1565809 (The Pile)

Max Activating Token Index: 951

Text #19

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1937041 (The Pile)

Max Activating Token Index: 840