Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2634 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1712. Min Act: -0.0002

Data Index: 89587 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1483. Min Act: -0.0002

Data Index: 1253519 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1663. Min Act: -0.0002

Data Index: 383759 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1651. Min Act: -0.0002

Data Index: 988322 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1531. Min Act: -0.0002

Data Index: 962461 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1545. Min Act: -0.0002

Data Index: 179440 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1573. Min Act: -0.0002

Data Index: 1102605 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1558. Min Act: -0.0002

Data Index: 382926 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1448. Min Act: -0.0002

Data Index: 611609 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1263. Min Act: -0.0002

Data Index: 994674 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1453. Min Act: -0.0002

Data Index: 1113980 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1481. Min Act: -0.0002

Data Index: 1252303 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1447. Min Act: -0.0002

Data Index: 417768 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1443. Min Act: -0.0002

Data Index: 196533 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1395. Min Act: -0.0002

Data Index: 768389 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1301. Min Act: -0.0002

Data Index: 583021 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1323. Min Act: -0.0002

Data Index: 576536 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1421. Min Act: -0.0002

Data Index: 1010848 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1457. Min Act: -0.0002

Data Index: 45793 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1400. Min Act: -0.0002

Data Index: 522570 (C4 (Web Text))

Max Activating Token Index: 462