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

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

Neuron 5499 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.3276. Min Act: -0.0001

Data Index: 1185774 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.1618. Min Act: -0.0001

Data Index: 992862 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.1767. Min Act: -0.0001

Data Index: 917765 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.1399. Min Act: -0.0001

Data Index: 777246 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.2797. Min Act: -0.0002

Data Index: 601783 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.9579. Min Act: -0.0001

Data Index: 268974 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.2533. Min Act: -0.0001

Data Index: 616082 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.1350. Min Act: -0.0002

Data Index: 1087373 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.0686. Min Act: -0.0001

Data Index: 1042559 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.9763. Min Act: -0.0001

Data Index: 961080 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.1268. Min Act: -0.0001

Data Index: 258993 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.9334. Min Act: -0.0002

Data Index: 415071 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.0951. Min Act: -0.0001

Data Index: 1261952 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.9805. Min Act: -0.0001

Data Index: 1131181 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.9987. Min Act: -0.0001

Data Index: 326698 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.9578. Min Act: -0.0001

Data Index: 718902 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.0139. Min Act: -0.0001

Data Index: 357659 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.9138. Min Act: -0.0001

Data Index: 172046 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.9545. Min Act: -0.0001

Data Index: 1214563 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.9919. Min Act: -0.0001

Data Index: 644022 (C4 (Web Text))

Max Activating Token Index: 165