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

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

Neuron 1202 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1875. Min Act: -0.0001

Data Index: 1365107 (Python Code)

Max Activating Token Index: 199

Text #1

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1033274 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1653. Min Act: -0.0001

Data Index: 1534836 (Python Code)

Max Activating Token Index: 43

Text #3

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1681. Min Act: -0.0001

Data Index: 772833 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1216068 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1612. Min Act: -0.0000

Data Index: 839415 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1533. Min Act: -0.0001

Data Index: 852585 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1549545 (Python Code)

Max Activating Token Index: 23

Text #8

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1481. Min Act: -0.0001

Data Index: 474426 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1421. Min Act: -0.0000

Data Index: 724309 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1405. Min Act: -0.0000

Data Index: 939847 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1593. Min Act: -0.0001

Data Index: 145510 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1448. Min Act: -0.0000

Data Index: 996009 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1420. Min Act: -0.0000

Data Index: 1643319 (Python Code)

Max Activating Token Index: 342

Text #14

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1361. Min Act: -0.0001

Data Index: 68942 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1438. Min Act: -0.0001

Data Index: 1346494 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1393. Min Act: -0.0001

Data Index: 389868 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1381. Min Act: -0.0000

Data Index: 1022045 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1206. Min Act: -0.0001

Data Index: 374224 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1415. Min Act: -0.0000

Data Index: 1370350 (Python Code)

Max Activating Token Index: 330