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

Dataset: The Pile

Neuron 3499 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3854. Min Act: -0.0000

Data Index: 1848706 (The Pile)

Max Activating Token Index: 745

Text #1

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.4128. Min Act: -0.0000

Data Index: 318631 (The Pile)

Max Activating Token Index: 354

Text #2

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3859. Min Act: -0.0000

Data Index: 1689666 (The Pile)

Max Activating Token Index: 794

Text #3

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3635. Min Act: -0.0000

Data Index: 1524851 (The Pile)

Max Activating Token Index: 171

Text #4

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3514. Min Act: -0.0000

Data Index: 274657 (The Pile)

Max Activating Token Index: 412

Text #5

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1923561 (The Pile)

Max Activating Token Index: 779

Text #6

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3167. Min Act: -0.0000

Data Index: 661208 (The Pile)

Max Activating Token Index: 906

Text #7

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2765. Min Act: -0.0000

Data Index: 990160 (The Pile)

Max Activating Token Index: 922

Text #8

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2971. Min Act: -0.0000

Data Index: 1460008 (The Pile)

Max Activating Token Index: 887

Text #9

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2834. Min Act: -0.0000

Data Index: 1626803 (The Pile)

Max Activating Token Index: 534

Text #10

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2828. Min Act: -0.0000

Data Index: 1587346 (The Pile)

Max Activating Token Index: 506

Text #11

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2855. Min Act: -0.0000

Data Index: 1881829 (The Pile)

Max Activating Token Index: 735

Text #12

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3057. Min Act: -0.0000

Data Index: 1720710 (The Pile)

Max Activating Token Index: 591

Text #13

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3056. Min Act: -0.0000

Data Index: 609116 (The Pile)

Max Activating Token Index: 1005

Text #14

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2826. Min Act: -0.0000

Data Index: 1551387 (The Pile)

Max Activating Token Index: 690

Text #15

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2667. Min Act: -0.0000

Data Index: 697347 (The Pile)

Max Activating Token Index: 694

Text #16

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2457. Min Act: -0.0000

Data Index: 990731 (The Pile)

Max Activating Token Index: 993

Text #17

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1446023 (The Pile)

Max Activating Token Index: 947

Text #18

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2652. Min Act: -0.0000

Data Index: 1531881 (The Pile)

Max Activating Token Index: 242

Text #19

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2565. Min Act: -0.0000

Data Index: 494682 (The Pile)

Max Activating Token Index: 390