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

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

Neuron 2040 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: 1.8467. Min Range: -1.8467

Max Act: 1.8467. Min Act: -0.0000

Data Index: 1470953 (Python Code)

Max Activating Token Index: 928

Text #1

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.6421. Min Act: -0.0000

Data Index: 1567354 (Python Code)

Max Activating Token Index: 914

Text #2

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.3630. Min Act: -0.0000

Data Index: 1460563 (Python Code)

Max Activating Token Index: 506

Text #3

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.5174. Min Act: -0.0000

Data Index: 1595280 (Python Code)

Max Activating Token Index: 767

Text #4

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.3887. Min Act: -0.0000

Data Index: 1604097 (Python Code)

Max Activating Token Index: 609

Text #5

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.4993. Min Act: -0.0000

Data Index: 1647878 (Python Code)

Max Activating Token Index: 646

Text #6

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.3162. Min Act: -0.0000

Data Index: 1567581 (Python Code)

Max Activating Token Index: 676

Text #7

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.3478. Min Act: -0.0000

Data Index: 1565133 (Python Code)

Max Activating Token Index: 499

Text #8

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.3204. Min Act: -0.0001

Data Index: 1419137 (Python Code)

Max Activating Token Index: 759

Text #9

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.3746. Min Act: -0.0000

Data Index: 1622012 (Python Code)

Max Activating Token Index: 140

Text #10

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.2321. Min Act: -0.0000

Data Index: 1607345 (Python Code)

Max Activating Token Index: 431

Text #11

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.3949. Min Act: -0.0000

Data Index: 1377496 (Python Code)

Max Activating Token Index: 287

Text #12

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.1422. Min Act: -0.0000

Data Index: 1484070 (Python Code)

Max Activating Token Index: 120

Text #13

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.1805. Min Act: -0.0000

Data Index: 1597621 (Python Code)

Max Activating Token Index: 291

Text #14

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.1149. Min Act: -0.0000

Data Index: 1451868 (Python Code)

Max Activating Token Index: 352

Text #15

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.2477. Min Act: -0.0000

Data Index: 1494477 (Python Code)

Max Activating Token Index: 719

Text #16

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.1922. Min Act: -0.0000

Data Index: 1631236 (Python Code)

Max Activating Token Index: 176

Text #17

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.1503. Min Act: -0.0000

Data Index: 1397586 (Python Code)

Max Activating Token Index: 1006

Text #18

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.1806. Min Act: -0.0000

Data Index: 1394724 (Python Code)

Max Activating Token Index: 765

Text #19

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.0440. Min Act: -0.0000

Data Index: 1452189 (Python Code)

Max Activating Token Index: 86