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

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

Neuron 1384 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1614804 (Python Code)

Max Activating Token Index: 45

Text #1

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.3055. Min Act: -0.0000

Data Index: 687310 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2678. Min Act: -0.0000

Data Index: 1062737 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1367152 (Python Code)

Max Activating Token Index: 891

Text #4

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2772. Min Act: -0.0000

Data Index: 1416590 (Python Code)

Max Activating Token Index: 182

Text #5

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2267. Min Act: -0.0000

Data Index: 971847 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2511. Min Act: -0.0000

Data Index: 1374108 (Python Code)

Max Activating Token Index: 200

Text #7

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2876. Min Act: -0.0000

Data Index: 1654547 (Python Code)

Max Activating Token Index: 701

Text #8

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2411. Min Act: -0.0000

Data Index: 515029 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2534. Min Act: -0.0000

Data Index: 193197 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2565. Min Act: -0.0000

Data Index: 73301 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2345. Min Act: -0.0000

Data Index: 1383518 (Python Code)

Max Activating Token Index: 50

Text #12

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2554. Min Act: -0.0000

Data Index: 1053833 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2629. Min Act: -0.0001

Data Index: 825511 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2352. Min Act: -0.0000

Data Index: 1597868 (Python Code)

Max Activating Token Index: 813

Text #15

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2334. Min Act: -0.0000

Data Index: 1365703 (Python Code)

Max Activating Token Index: 534

Text #16

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2635. Min Act: -0.0000

Data Index: 1570177 (Python Code)

Max Activating Token Index: 834

Text #17

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2366. Min Act: -0.0000

Data Index: 352147 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1479489 (Python Code)

Max Activating Token Index: 264

Text #19

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2206. Min Act: -0.0000

Data Index: 782909 (C4 (Web Text))

Max Activating Token Index: 317