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

Dataset: The Pile

Neuron 5029 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.9448. Min Act: -0.0001

Data Index: 1752450 (The Pile)

Max Activating Token Index: 247

Text #1

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.6623. Min Act: -0.0000

Data Index: 474754 (The Pile)

Max Activating Token Index: 920

Text #2

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8025. Min Act: -0.0000

Data Index: 829521 (The Pile)

Max Activating Token Index: 322

Text #3

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.5365. Min Act: -0.0000

Data Index: 430685 (The Pile)

Max Activating Token Index: 20

Text #4

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.4981. Min Act: -0.0000

Data Index: 1091663 (The Pile)

Max Activating Token Index: 928

Text #5

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.4966. Min Act: -0.0000

Data Index: 19222 (The Pile)

Max Activating Token Index: 84

Text #6

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.5428. Min Act: -0.0000

Data Index: 90225 (The Pile)

Max Activating Token Index: 6

Text #7

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.5411. Min Act: -0.0000

Data Index: 1676691 (The Pile)

Max Activating Token Index: 164

Text #8

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.4897. Min Act: -0.0001

Data Index: 171789 (The Pile)

Max Activating Token Index: 94

Text #9

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.4063. Min Act: -0.0000

Data Index: 1996256 (The Pile)

Max Activating Token Index: 257

Text #10

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.3663. Min Act: -0.0000

Data Index: 212718 (The Pile)

Max Activating Token Index: 369

Text #11

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.3318. Min Act: -0.0000

Data Index: 1129194 (The Pile)

Max Activating Token Index: 83

Text #12

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.3203. Min Act: -0.0000

Data Index: 1587341 (The Pile)

Max Activating Token Index: 211

Text #13

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.3909. Min Act: -0.0000

Data Index: 704567 (The Pile)

Max Activating Token Index: 443

Text #14

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.2696. Min Act: -0.0001

Data Index: 952243 (The Pile)

Max Activating Token Index: 434

Text #15

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.3579. Min Act: -0.0000

Data Index: 1705441 (The Pile)

Max Activating Token Index: 221

Text #16

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.2475. Min Act: -0.0000

Data Index: 576935 (The Pile)

Max Activating Token Index: 229

Text #17

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.4322. Min Act: -0.0000

Data Index: 888644 (The Pile)

Max Activating Token Index: 109

Text #18

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.2009. Min Act: -0.0000

Data Index: 1435986 (The Pile)

Max Activating Token Index: 29

Text #19

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.3910. Min Act: -0.0000

Data Index: 820364 (The Pile)

Max Activating Token Index: 846