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

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

Neuron 4738 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.4633. Min Act: -0.0000

Data Index: 1485156 (Python Code)

Max Activating Token Index: 88

Text #1

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.3362. Min Act: -0.0000

Data Index: 779686 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.2887. Min Act: -0.0000

Data Index: 611678 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.1860. Min Act: -0.0000

Data Index: 409819 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.2555. Min Act: -0.0000

Data Index: 1144105 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.2894. Min Act: -0.0000

Data Index: 824749 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.2028. Min Act: -0.0000

Data Index: 940125 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.2332. Min Act: -0.0000

Data Index: 577435 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.2173. Min Act: -0.0000

Data Index: 892592 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.1809. Min Act: -0.0000

Data Index: 1517172 (Python Code)

Max Activating Token Index: 160

Text #10

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.1625. Min Act: -0.0000

Data Index: 770828 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.1696. Min Act: -0.0000

Data Index: 398789 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.1043. Min Act: -0.0000

Data Index: 1505711 (Python Code)

Max Activating Token Index: 104

Text #13

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.1395. Min Act: -0.0000

Data Index: 880440 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.1670. Min Act: -0.0000

Data Index: 1081367 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.1263. Min Act: -0.0000

Data Index: 137542 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.1250. Min Act: -0.0000

Data Index: 1174043 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.1308. Min Act: -0.0000

Data Index: 286757 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.0996. Min Act: -0.0000

Data Index: 977683 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.1765. Min Act: -0.0000

Data Index: 1051631 (C4 (Web Text))

Max Activating Token Index: 371