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

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

Neuron 3121 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.3303. Min Act: -0.0001

Data Index: 919905 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2554. Min Act: -0.0001

Data Index: 266375 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2809. Min Act: -0.0001

Data Index: 464557 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2983. Min Act: -0.0001

Data Index: 314453 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2613. Min Act: -0.0001

Data Index: 1036101 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2438. Min Act: -0.0001

Data Index: 1266618 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2698. Min Act: -0.0001

Data Index: 797478 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2587. Min Act: -0.0001

Data Index: 58506 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2409. Min Act: -0.0001

Data Index: 571951 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2526. Min Act: -0.0001

Data Index: 1001082 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2417. Min Act: -0.0001

Data Index: 995343 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2576. Min Act: -0.0001

Data Index: 328884 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2603. Min Act: -0.0001

Data Index: 291936 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2494. Min Act: -0.0001

Data Index: 100022 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2474. Min Act: -0.0001

Data Index: 203717 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2633. Min Act: -0.0001

Data Index: 1324432 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2408. Min Act: -0.0001

Data Index: 1283577 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2481. Min Act: -0.0001

Data Index: 1285848 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2373. Min Act: -0.0001

Data Index: 1241585 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2387. Min Act: -0.0001

Data Index: 94948 (C4 (Web Text))

Max Activating Token Index: 245