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

Dataset: The Pile

Neuron 541 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.3828. Min Act: -0.0000

Data Index: 450329 (The Pile)

Max Activating Token Index: 611

Text #1

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.4276. Min Act: -0.0000

Data Index: 104801 (The Pile)

Max Activating Token Index: 710

Text #2

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.4099. Min Act: -0.0000

Data Index: 1448070 (The Pile)

Max Activating Token Index: 1006

Text #3

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.4180. Min Act: -0.0000

Data Index: 1063527 (The Pile)

Max Activating Token Index: 631

Text #4

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.4616. Min Act: -0.0000

Data Index: 510946 (The Pile)

Max Activating Token Index: 94

Text #5

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.4716. Min Act: -0.0000

Data Index: 740106 (The Pile)

Max Activating Token Index: 943

Text #6

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.4191. Min Act: -0.0000

Data Index: 1904487 (The Pile)

Max Activating Token Index: 986

Text #7

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.4974. Min Act: -0.0000

Data Index: 1925533 (The Pile)

Max Activating Token Index: 1018

Text #8

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.3777. Min Act: -0.0000

Data Index: 1476080 (The Pile)

Max Activating Token Index: 1002

Text #9

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.4428. Min Act: -0.0000

Data Index: 751764 (The Pile)

Max Activating Token Index: 790

Text #10

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.3897. Min Act: -0.0000

Data Index: 4111 (The Pile)

Max Activating Token Index: 982

Text #11

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.3851. Min Act: -0.0000

Data Index: 682772 (The Pile)

Max Activating Token Index: 368

Text #12

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.2500. Min Act: -0.0000

Data Index: 1597382 (The Pile)

Max Activating Token Index: 956

Text #13

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.3367. Min Act: -0.0000

Data Index: 922060 (The Pile)

Max Activating Token Index: 884

Text #14

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.3640. Min Act: -0.0000

Data Index: 449056 (The Pile)

Max Activating Token Index: 552

Text #15

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.1726. Min Act: -0.0000

Data Index: 1645408 (The Pile)

Max Activating Token Index: 782

Text #16

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.1477. Min Act: -0.0000

Data Index: 219735 (The Pile)

Max Activating Token Index: 440

Text #17

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.3259. Min Act: -0.0000

Data Index: 1107728 (The Pile)

Max Activating Token Index: 616

Text #18

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.4327. Min Act: -0.0000

Data Index: 846633 (The Pile)

Max Activating Token Index: 806

Text #19

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.2508. Min Act: -0.0000

Data Index: 497107 (The Pile)

Max Activating Token Index: 555