Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3652 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.4329. Min Act: -0.0001

Data Index: 1238513 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.2684. Min Act: -0.0001

Data Index: 816411 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1983. Min Act: -0.0001

Data Index: 948357 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1974. Min Act: -0.0001

Data Index: 604392 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1185. Min Act: -0.0002

Data Index: 465744 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1815. Min Act: -0.0001

Data Index: 844435 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1637. Min Act: -0.0002

Data Index: 25225 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1795. Min Act: -0.0001

Data Index: 1166646 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.2192. Min Act: -0.0001

Data Index: 583379 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1386. Min Act: -0.0002

Data Index: 874226 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.0736. Min Act: -0.0002

Data Index: 882639 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1092. Min Act: -0.0002

Data Index: 690890 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1446. Min Act: -0.0001

Data Index: 910648 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1001. Min Act: -0.0001

Data Index: 1199090 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1658. Min Act: -0.0002

Data Index: 198128 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1276. Min Act: -0.0001

Data Index: 654990 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.0871. Min Act: -0.0002

Data Index: 90506 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1095. Min Act: -0.0001

Data Index: 908105 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1169. Min Act: -0.0002

Data Index: 707334 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1146. Min Act: -0.0002

Data Index: 567314 (C4 (Web Text))

Max Activating Token Index: 990