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

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

Neuron 1934 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.4848. Min Act: -0.0000

Data Index: 1619293 (Python Code)

Max Activating Token Index: 49

Text #1

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.4069. Min Act: -0.0000

Data Index: 268215 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.3821. Min Act: -0.0000

Data Index: 1590049 (Python Code)

Max Activating Token Index: 373

Text #3

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.3625. Min Act: -0.0000

Data Index: 1606665 (Python Code)

Max Activating Token Index: 568

Text #4

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.3181. Min Act: -0.0000

Data Index: 188116 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.2418. Min Act: -0.0000

Data Index: 1199279 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.3147. Min Act: -0.0000

Data Index: 1375376 (Python Code)

Max Activating Token Index: 206

Text #7

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.2149. Min Act: -0.0000

Data Index: 515459 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.3165. Min Act: -0.0000

Data Index: 96102 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.1930. Min Act: 0.0000

Data Index: 1551570 (Python Code)

Max Activating Token Index: 985

Text #10

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.0794. Min Act: 0.0000

Data Index: 1422463 (Python Code)

Max Activating Token Index: 163

Text #11

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.2116. Min Act: -0.0000

Data Index: 829540 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.0897. Min Act: -0.0000

Data Index: 316239 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.0256. Min Act: -0.0000

Data Index: 1051951 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.0469. Min Act: -0.0000

Data Index: 1536247 (Python Code)

Max Activating Token Index: 463

Text #15

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.0608. Min Act: -0.0000

Data Index: 1633689 (Python Code)

Max Activating Token Index: 605

Text #16

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.0494. Min Act: -0.0000

Data Index: 1505076 (Python Code)

Max Activating Token Index: 58

Text #17

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.0900. Min Act: -0.0000

Data Index: 1461599 (Python Code)

Max Activating Token Index: 123

Text #18

Max Range: 1.4848. Min Range: -1.4848

Max Act: 0.9954. Min Act: -0.0000

Data Index: 1583587 (Python Code)

Max Activating Token Index: 485

Text #19

Max Range: 1.4848. Min Range: -1.4848

Max Act: 0.9859. Min Act: -0.0000

Data Index: 1631378 (Python Code)

Max Activating Token Index: 465