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

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

Neuron 1467 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1893. Min Act: -0.0001

Data Index: 145350 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1584. Min Act: -0.0002

Data Index: 707364 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1401. Min Act: -0.0002

Data Index: 860662 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1552. Min Act: -0.0001

Data Index: 1227490 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1534. Min Act: -0.0002

Data Index: 1278749 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1439. Min Act: -0.0002

Data Index: 656925 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1437. Min Act: -0.0002

Data Index: 1156452 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1383. Min Act: -0.0001

Data Index: 472493 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1590. Min Act: -0.0001

Data Index: 137570 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1434. Min Act: -0.0001

Data Index: 283679 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1408. Min Act: -0.0002

Data Index: 1102785 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1362. Min Act: -0.0002

Data Index: 897812 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1519. Min Act: -0.0002

Data Index: 642133 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1446. Min Act: -0.0002

Data Index: 363486 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1454. Min Act: -0.0002

Data Index: 113190 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1431. Min Act: -0.0002

Data Index: 942913 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1465. Min Act: -0.0002

Data Index: 504526 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1432. Min Act: -0.0002

Data Index: 36934 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1269. Min Act: -0.0002

Data Index: 624565 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1469. Min Act: -0.0002

Data Index: 281284 (C4 (Web Text))

Max Activating Token Index: 373