Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 498 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1556. Min Act: -0.0002

Data Index: 260007 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1533. Min Act: -0.0002

Data Index: 38045 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1529. Min Act: -0.0002

Data Index: 394667 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1477. Min Act: -0.0002

Data Index: 355663 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1536. Min Act: -0.0002

Data Index: 301565 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1476. Min Act: -0.0002

Data Index: 1178118 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1479. Min Act: -0.0002

Data Index: 945027 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1475. Min Act: -0.0002

Data Index: 1133158 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1426. Min Act: -0.0002

Data Index: 929402 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1492. Min Act: -0.0002

Data Index: 298690 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1479. Min Act: -0.0002

Data Index: 893745 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1472. Min Act: -0.0002

Data Index: 1105897 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1469. Min Act: -0.0002

Data Index: 161755 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1493. Min Act: -0.0002

Data Index: 408673 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1454. Min Act: -0.0002

Data Index: 861066 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1435. Min Act: -0.0002

Data Index: 1308566 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1376. Min Act: -0.0002

Data Index: 105080 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1438. Min Act: -0.0002

Data Index: 481431 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1437. Min Act: -0.0002

Data Index: 930988 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1389. Min Act: -0.0002

Data Index: 1340150 (C4 (Web Text))

Max Activating Token Index: 63