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

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

Neuron 1452 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9726. Min Range: -2.9726

Max Act: 2.9726. Min Act: -0.0000

Data Index: 156106 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 2.9726. Min Range: -2.9726

Max Act: 2.8412. Min Act: -0.0000

Data Index: 925903 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 2.9726. Min Range: -2.9726

Max Act: 2.5048. Min Act: -0.0000

Data Index: 1397410 (Python Code)

Max Activating Token Index: 379

Text #3

Max Range: 2.9726. Min Range: -2.9726

Max Act: 2.3248. Min Act: -0.0000

Data Index: 1347392 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 2.9726. Min Range: -2.9726

Max Act: 2.5439. Min Act: -0.0000

Data Index: 1511605 (Python Code)

Max Activating Token Index: 409

Text #5

Max Range: 2.9726. Min Range: -2.9726

Max Act: 2.3317. Min Act: -0.0000

Data Index: 1492230 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 2.9726. Min Range: -2.9726

Max Act: 1.8269. Min Act: -0.0000

Data Index: 266452 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 2.9726. Min Range: -2.9726

Max Act: 2.1300. Min Act: -0.0000

Data Index: 1552498 (Python Code)

Max Activating Token Index: 716

Text #8

Max Range: 2.9726. Min Range: -2.9726

Max Act: 1.8049. Min Act: -0.0000

Data Index: 940496 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 2.9726. Min Range: -2.9726

Max Act: 1.9924. Min Act: -0.0000

Data Index: 249222 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 2.9726. Min Range: -2.9726

Max Act: 2.1048. Min Act: -0.0000

Data Index: 782401 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 2.9726. Min Range: -2.9726

Max Act: 1.9462. Min Act: -0.0000

Data Index: 1623467 (Python Code)

Max Activating Token Index: 456

Text #12

Max Range: 2.9726. Min Range: -2.9726

Max Act: 2.0930. Min Act: -0.0000

Data Index: 562022 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 2.9726. Min Range: -2.9726

Max Act: 2.0133. Min Act: -0.0000

Data Index: 1502504 (Python Code)

Max Activating Token Index: 104

Text #14

Max Range: 2.9726. Min Range: -2.9726

Max Act: 2.0664. Min Act: -0.0000

Data Index: 1608148 (Python Code)

Max Activating Token Index: 950

Text #15

Max Range: 2.9726. Min Range: -2.9726

Max Act: 2.1593. Min Act: -0.0000

Data Index: 512496 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 2.9726. Min Range: -2.9726

Max Act: 1.9075. Min Act: -0.0000

Data Index: 1419495 (Python Code)

Max Activating Token Index: 399

Text #17

Max Range: 2.9726. Min Range: -2.9726

Max Act: 1.5302. Min Act: -0.0000

Data Index: 1325927 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 2.9726. Min Range: -2.9726

Max Act: 1.5582. Min Act: -0.0000

Data Index: 735442 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 2.9726. Min Range: -2.9726

Max Act: 1.1134. Min Act: -0.0000

Data Index: 131931 (C4 (Web Text))

Max Activating Token Index: 996