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

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

Neuron 896 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.3307. Min Act: -0.0000

Data Index: 1580251 (Python Code)

Max Activating Token Index: 933

Text #1

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.3604. Min Act: -0.0000

Data Index: 1512334 (Python Code)

Max Activating Token Index: 587

Text #2

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.2706. Min Act: -0.0000

Data Index: 211022 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.2325. Min Act: -0.0000

Data Index: 982052 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.2078. Min Act: -0.0000

Data Index: 1065387 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.1845. Min Act: -0.0000

Data Index: 332576 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.1133. Min Act: -0.0000

Data Index: 317779 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.1673. Min Act: -0.0000

Data Index: 255784 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.1606. Min Act: -0.0000

Data Index: 679724 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.1179. Min Act: -0.0000

Data Index: 506390 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.1441. Min Act: -0.0000

Data Index: 1135100 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.0725. Min Act: -0.0000

Data Index: 532889 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 1.3604. Min Range: -1.3604

Max Act: 0.9923. Min Act: -0.0000

Data Index: 1603305 (Python Code)

Max Activating Token Index: 524

Text #13

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.0239. Min Act: -0.0000

Data Index: 1538214 (Python Code)

Max Activating Token Index: 940

Text #14

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1147820 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.0934. Min Act: -0.0000

Data Index: 758365 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.0241. Min Act: -0.0000

Data Index: 1399761 (Python Code)

Max Activating Token Index: 306

Text #17

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.0807. Min Act: -0.0000

Data Index: 1456537 (Python Code)

Max Activating Token Index: 280

Text #18

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.0106. Min Act: -0.0000

Data Index: 215440 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.0293. Min Act: -0.0000

Data Index: 1236438 (C4 (Web Text))

Max Activating Token Index: 319