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

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

Neuron 5867 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1230. Min Range: -2.1230

Max Act: 2.1230. Min Act: -0.0000

Data Index: 1183162 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.9014. Min Act: -0.0000

Data Index: 1238411 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.9746. Min Act: -0.0000

Data Index: 879696 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.8627. Min Act: -0.0000

Data Index: 776139 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.7221. Min Act: -0.0000

Data Index: 331206 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.8497. Min Act: -0.0000

Data Index: 1321661 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.7322. Min Act: -0.0000

Data Index: 257837 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.7501. Min Act: -0.0000

Data Index: 693597 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.4995. Min Act: -0.0000

Data Index: 1351610 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.5823. Min Act: -0.0000

Data Index: 1237613 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.3517. Min Act: -0.0000

Data Index: 491281 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.5376. Min Act: -0.0000

Data Index: 535053 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.5282. Min Act: -0.0000

Data Index: 237992 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.6268. Min Act: -0.0000

Data Index: 898790 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.4338. Min Act: -0.0000

Data Index: 787277 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.6100. Min Act: -0.0000

Data Index: 1323148 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.4527. Min Act: -0.0000

Data Index: 387360 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.5219. Min Act: -0.0000

Data Index: 921402 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.4271. Min Act: -0.0000

Data Index: 448537 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 2.1230. Min Range: -2.1230

Max Act: 1.4934. Min Act: -0.0000

Data Index: 824576 (C4 (Web Text))

Max Activating Token Index: 493