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

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

Neuron 2319 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1897. Min Act: -0.0001

Data Index: 109092 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1891. Min Act: -0.0001

Data Index: 1028501 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1799. Min Act: -0.0001

Data Index: 1217878 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1701. Min Act: -0.0001

Data Index: 225180 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1678. Min Act: -0.0001

Data Index: 491130 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1579. Min Act: -0.0001

Data Index: 429381 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1571. Min Act: -0.0001

Data Index: 116552 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1603. Min Act: -0.0001

Data Index: 536445 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1496. Min Act: -0.0001

Data Index: 1105528 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1493. Min Act: -0.0001

Data Index: 542540 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1407. Min Act: -0.0001

Data Index: 857980 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1440. Min Act: -0.0001

Data Index: 1183849 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1417. Min Act: -0.0001

Data Index: 612654 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1427. Min Act: -0.0001

Data Index: 960699 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1424. Min Act: -0.0001

Data Index: 952381 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1534. Min Act: -0.0001

Data Index: 259297 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1410. Min Act: -0.0001

Data Index: 452356 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1384. Min Act: -0.0001

Data Index: 1122264 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1421. Min Act: -0.0001

Data Index: 298567 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1478. Min Act: -0.0001

Data Index: 1009283 (C4 (Web Text))

Max Activating Token Index: 933