Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 701 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.2305. Min Act: -0.0001

Data Index: 92378 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1752. Min Act: -0.0001

Data Index: 690561 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1682. Min Act: -0.0001

Data Index: 83713 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1934. Min Act: -0.0001

Data Index: 1022829 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1667. Min Act: -0.0001

Data Index: 584422 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1588. Min Act: -0.0001

Data Index: 37182 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1713. Min Act: -0.0001

Data Index: 239878 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1686. Min Act: -0.0001

Data Index: 662328 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1600. Min Act: -0.0001

Data Index: 179745 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1537. Min Act: -0.0001

Data Index: 383352 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1623. Min Act: -0.0001

Data Index: 237025 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1449. Min Act: -0.0001

Data Index: 1021226 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1409. Min Act: -0.0001

Data Index: 1220915 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1554. Min Act: -0.0001

Data Index: 329963 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1536. Min Act: -0.0001

Data Index: 1251219 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1522. Min Act: -0.0001

Data Index: 1456211 (Python Code)

Max Activating Token Index: 297

Text #16

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1475. Min Act: -0.0001

Data Index: 1192439 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1576. Min Act: -0.0001

Data Index: 94807 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1568. Min Act: -0.0001

Data Index: 1279327 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1506. Min Act: -0.0001

Data Index: 1305011 (C4 (Web Text))

Max Activating Token Index: 304