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

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

Neuron 1117 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1634. Min Act: -0.0005

Data Index: 858369 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1615. Min Act: -0.0005

Data Index: 971622 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1546. Min Act: -0.0005

Data Index: 1330423 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1537. Min Act: -0.0005

Data Index: 277264 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1516. Min Act: -0.0005

Data Index: 1157504 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1397. Min Act: -0.0005

Data Index: 1124065 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1443. Min Act: -0.0005

Data Index: 523019 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1496. Min Act: -0.0005

Data Index: 1843 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1481. Min Act: -0.0005

Data Index: 179593 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1423. Min Act: -0.0005

Data Index: 702327 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1415. Min Act: -0.0005

Data Index: 584597 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1293. Min Act: -0.0005

Data Index: 107432 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1326. Min Act: -0.0005

Data Index: 536652 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1386. Min Act: -0.0005

Data Index: 1071517 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1377. Min Act: -0.0005

Data Index: 603558 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1267. Min Act: -0.0005

Data Index: 802364 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1300. Min Act: -0.0005

Data Index: 1141711 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1367. Min Act: -0.0005

Data Index: 1270839 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1290. Min Act: -0.0005

Data Index: 156497 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1286. Min Act: -0.0005

Data Index: 1098054 (C4 (Web Text))

Max Activating Token Index: 303