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

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

Neuron 4915 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.3279. Min Act: -0.0000

Data Index: 1535684 (Python Code)

Max Activating Token Index: 725

Text #1

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.0443. Min Act: -0.0000

Data Index: 1463107 (Python Code)

Max Activating Token Index: 568

Text #2

Max Range: 1.3279. Min Range: -1.3279

Max Act: 0.9382. Min Act: -0.0000

Data Index: 1641562 (Python Code)

Max Activating Token Index: 529

Text #3

Max Range: 1.3279. Min Range: -1.3279

Max Act: 0.9478. Min Act: -0.0000

Data Index: 1638612 (Python Code)

Max Activating Token Index: 474

Text #4

Max Range: 1.3279. Min Range: -1.3279

Max Act: 0.8759. Min Act: -0.0000

Data Index: 1502728 (Python Code)

Max Activating Token Index: 163

Text #5

Max Range: 1.3279. Min Range: -1.3279

Max Act: 0.9326. Min Act: -0.0000

Data Index: 1652006 (Python Code)

Max Activating Token Index: 399

Text #6

Max Range: 1.3279. Min Range: -1.3279

Max Act: 0.9687. Min Act: -0.0000

Data Index: 1524338 (Python Code)

Max Activating Token Index: 609

Text #7

Max Range: 1.3279. Min Range: -1.3279

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1451342 (Python Code)

Max Activating Token Index: 807

Text #8

Max Range: 1.3279. Min Range: -1.3279

Max Act: 0.8146. Min Act: -0.0000

Data Index: 1425404 (Python Code)

Max Activating Token Index: 779

Text #9

Max Range: 1.3279. Min Range: -1.3279

Max Act: 0.9272. Min Act: -0.0000

Data Index: 1388532 (Python Code)

Max Activating Token Index: 930

Text #10

Max Range: 1.3279. Min Range: -1.3279

Max Act: 0.7908. Min Act: -0.0000

Data Index: 1424561 (Python Code)

Max Activating Token Index: 479

Text #11

Max Range: 1.3279. Min Range: -1.3279

Max Act: 0.7800. Min Act: -0.0000

Data Index: 1494928 (Python Code)

Max Activating Token Index: 398

Text #12

Max Range: 1.3279. Min Range: -1.3279

Max Act: 0.6149. Min Act: -0.0000

Data Index: 1437617 (Python Code)

Max Activating Token Index: 170

Text #13

Max Range: 1.3279. Min Range: -1.3279

Max Act: 0.6553. Min Act: -0.0000

Data Index: 1451705 (Python Code)

Max Activating Token Index: 693

Text #14

Max Range: 1.3279. Min Range: -1.3279

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1414206 (Python Code)

Max Activating Token Index: 506

Text #15

Max Range: 1.3279. Min Range: -1.3279

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1650775 (Python Code)

Max Activating Token Index: 237

Text #16

Max Range: 1.3279. Min Range: -1.3279

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1607869 (Python Code)

Max Activating Token Index: 84

Text #17

Max Range: 1.3279. Min Range: -1.3279

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1407825 (Python Code)

Max Activating Token Index: 329

Text #18

Max Range: 1.3279. Min Range: -1.3279

Max Act: 0.5983. Min Act: -0.0000

Data Index: 1571977 (Python Code)

Max Activating Token Index: 528

Text #19

Max Range: 1.3279. Min Range: -1.3279

Max Act: 0.6574. Min Act: -0.0000

Data Index: 1650668 (Python Code)

Max Activating Token Index: 819