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

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

Neuron 1808 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.6325. Min Act: -0.0000

Data Index: 1502155 (Python Code)

Max Activating Token Index: 900

Text #1

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5102. Min Act: -0.0000

Data Index: 1452135 (Python Code)

Max Activating Token Index: 671

Text #2

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.3889. Min Act: -0.0000

Data Index: 475466 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.4683. Min Act: -0.0000

Data Index: 1605687 (Python Code)

Max Activating Token Index: 229

Text #4

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.4687. Min Act: -0.0000

Data Index: 1570292 (Python Code)

Max Activating Token Index: 991

Text #5

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.4602. Min Act: -0.0000

Data Index: 1010786 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.4987. Min Act: -0.0000

Data Index: 912806 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.4220. Min Act: -0.0000

Data Index: 982789 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.3221. Min Act: -0.0000

Data Index: 168956 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.3533. Min Act: -0.0000

Data Index: 1062420 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.2707. Min Act: -0.0000

Data Index: 307202 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.3381. Min Act: -0.0000

Data Index: 1239078 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.4281. Min Act: -0.0000

Data Index: 1499580 (Python Code)

Max Activating Token Index: 162

Text #13

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.3502. Min Act: -0.0000

Data Index: 1347784 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.2702. Min Act: -0.0000

Data Index: 71742 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.3006. Min Act: -0.0000

Data Index: 184711 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.2765. Min Act: -0.0000

Data Index: 489302 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.3482. Min Act: -0.0000

Data Index: 742458 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.3506. Min Act: -0.0000

Data Index: 511056 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.1922. Min Act: -0.0000

Data Index: 426936 (C4 (Web Text))

Max Activating Token Index: 215