Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4517 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1028. Min Range: -2.1028

Max Act: 2.1028. Min Act: -0.0000

Data Index: 590424 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 2.1028. Min Range: -2.1028

Max Act: 1.8501. Min Act: -0.0000

Data Index: 1216328 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 2.1028. Min Range: -2.1028

Max Act: 1.6619. Min Act: -0.0000

Data Index: 531690 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 2.1028. Min Range: -2.1028

Max Act: 1.8244. Min Act: -0.0001

Data Index: 154663 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 2.1028. Min Range: -2.1028

Max Act: 1.6991. Min Act: -0.0000

Data Index: 1357429 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 2.1028. Min Range: -2.1028

Max Act: 1.8602. Min Act: -0.0000

Data Index: 29438 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 2.1028. Min Range: -2.1028

Max Act: 1.5553. Min Act: -0.0000

Data Index: 158527 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 2.1028. Min Range: -2.1028

Max Act: 1.5271. Min Act: -0.0000

Data Index: 222707 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 2.1028. Min Range: -2.1028

Max Act: 1.4958. Min Act: -0.0001

Data Index: 233880 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 2.1028. Min Range: -2.1028

Max Act: 1.4222. Min Act: -0.0000

Data Index: 7728 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 2.1028. Min Range: -2.1028

Max Act: 1.4169. Min Act: -0.0000

Data Index: 1150991 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 2.1028. Min Range: -2.1028

Max Act: 1.4716. Min Act: -0.0001

Data Index: 1306090 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 2.1028. Min Range: -2.1028

Max Act: 1.4014. Min Act: -0.0001

Data Index: 1157218 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 2.1028. Min Range: -2.1028

Max Act: 1.3613. Min Act: -0.0000

Data Index: 646980 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 2.1028. Min Range: -2.1028

Max Act: 1.3697. Min Act: -0.0001

Data Index: 517420 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 2.1028. Min Range: -2.1028

Max Act: 1.2921. Min Act: -0.0000

Data Index: 749825 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 2.1028. Min Range: -2.1028

Max Act: 1.3328. Min Act: -0.0001

Data Index: 1184146 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 2.1028. Min Range: -2.1028

Max Act: 1.4062. Min Act: -0.0000

Data Index: 139791 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 2.1028. Min Range: -2.1028

Max Act: 1.1720. Min Act: -0.0000

Data Index: 288979 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 2.1028. Min Range: -2.1028

Max Act: 1.2439. Min Act: -0.0000

Data Index: 690126 (C4 (Web Text))

Max Activating Token Index: 411