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

Dataset: The Pile

Neuron 2629 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6004. Min Range: -3.6004

Max Act: 3.6004. Min Act: -0.0000

Data Index: 875959 (The Pile)

Max Activating Token Index: 304

Text #1

Max Range: 3.6004. Min Range: -3.6004

Max Act: 3.0731. Min Act: -0.0000

Data Index: 1913332 (The Pile)

Max Activating Token Index: 30

Text #2

Max Range: 3.6004. Min Range: -3.6004

Max Act: 2.9367. Min Act: -0.0000

Data Index: 1462833 (The Pile)

Max Activating Token Index: 885

Text #3

Max Range: 3.6004. Min Range: -3.6004

Max Act: 3.0395. Min Act: -0.0000

Data Index: 1429451 (The Pile)

Max Activating Token Index: 735

Text #4

Max Range: 3.6004. Min Range: -3.6004

Max Act: 3.2842. Min Act: -0.0000

Data Index: 1404639 (The Pile)

Max Activating Token Index: 39

Text #5

Max Range: 3.6004. Min Range: -3.6004

Max Act: 3.1634. Min Act: -0.0000

Data Index: 1698923 (The Pile)

Max Activating Token Index: 818

Text #6

Max Range: 3.6004. Min Range: -3.6004

Max Act: 3.1437. Min Act: -0.0000

Data Index: 989706 (The Pile)

Max Activating Token Index: 101

Text #7

Max Range: 3.6004. Min Range: -3.6004

Max Act: 2.8861. Min Act: -0.0000

Data Index: 1621347 (The Pile)

Max Activating Token Index: 148

Text #8

Max Range: 3.6004. Min Range: -3.6004

Max Act: 2.8617. Min Act: -0.0000

Data Index: 260057 (The Pile)

Max Activating Token Index: 652

Text #9

Max Range: 3.6004. Min Range: -3.6004

Max Act: 2.8493. Min Act: -0.0000

Data Index: 531399 (The Pile)

Max Activating Token Index: 498

Text #10

Max Range: 3.6004. Min Range: -3.6004

Max Act: 2.8182. Min Act: -0.0000

Data Index: 1558382 (The Pile)

Max Activating Token Index: 563

Text #11

Max Range: 3.6004. Min Range: -3.6004

Max Act: 2.7716. Min Act: -0.0000

Data Index: 1059926 (The Pile)

Max Activating Token Index: 1007

Text #12

Max Range: 3.6004. Min Range: -3.6004

Max Act: 2.7198. Min Act: -0.0000

Data Index: 348523 (The Pile)

Max Activating Token Index: 51

Text #13

Max Range: 3.6004. Min Range: -3.6004

Max Act: 2.7147. Min Act: -0.0000

Data Index: 1096791 (The Pile)

Max Activating Token Index: 712

Text #14

Max Range: 3.6004. Min Range: -3.6004

Max Act: 2.4754. Min Act: -0.0000

Data Index: 1523608 (The Pile)

Max Activating Token Index: 853

Text #15

Max Range: 3.6004. Min Range: -3.6004

Max Act: 2.4910. Min Act: -0.0000

Data Index: 152342 (The Pile)

Max Activating Token Index: 326

Text #16

Max Range: 3.6004. Min Range: -3.6004

Max Act: 2.5711. Min Act: -0.0000

Data Index: 1883398 (The Pile)

Max Activating Token Index: 515

Text #17

Max Range: 3.6004. Min Range: -3.6004

Max Act: 2.3408. Min Act: -0.0000

Data Index: 1964840 (The Pile)

Max Activating Token Index: 621

Text #18

Max Range: 3.6004. Min Range: -3.6004

Max Act: 2.4242. Min Act: -0.0000

Data Index: 256933 (The Pile)

Max Activating Token Index: 803

Text #19

Max Range: 3.6004. Min Range: -3.6004

Max Act: 2.6473. Min Act: -0.0000

Data Index: 1872100 (The Pile)

Max Activating Token Index: 226