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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3142 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.6931. Min Act: -0.0001

Data Index: 112211 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.5356. Min Act: -0.0001

Data Index: 519343 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.6905. Min Act: -0.0001

Data Index: 1094206 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.6232. Min Act: -0.0001

Data Index: 375387 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.5307. Min Act: -0.0001

Data Index: 7045 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.3996. Min Act: -0.0001

Data Index: 947063 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.4848. Min Act: -0.0001

Data Index: 204499 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.4930. Min Act: -0.0001

Data Index: 58399 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.5559. Min Act: -0.0001

Data Index: 396773 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.3966. Min Act: -0.0001

Data Index: 1198961 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.3425. Min Act: -0.0001

Data Index: 934483 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.4434. Min Act: -0.0001

Data Index: 781454 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.3037. Min Act: -0.0001

Data Index: 621056 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.3539. Min Act: -0.0001

Data Index: 308414 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.4319. Min Act: -0.0001

Data Index: 1129832 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.3629. Min Act: -0.0001

Data Index: 309858 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.3340. Min Act: -0.0001

Data Index: 922474 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.3253. Min Act: -0.0001

Data Index: 704714 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.2354. Min Act: -0.0001

Data Index: 448987 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 1.6931. Min Range: -1.6931

Max Act: 1.2156. Min Act: -0.0001

Data Index: 521727 (C4 (Web Text))

Max Activating Token Index: 555