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

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

Neuron 3986 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1751. Min Act: -0.0001

Data Index: 1335153 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1669. Min Act: -0.0001

Data Index: 1259835 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1791. Min Act: -0.0001

Data Index: 1457206 (Python Code)

Max Activating Token Index: 583

Text #3

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1502. Min Act: -0.0001

Data Index: 1494720 (Python Code)

Max Activating Token Index: 880

Text #4

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1592. Min Act: -0.0001

Data Index: 807932 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1570. Min Act: -0.0001

Data Index: 422879 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1663. Min Act: -0.0001

Data Index: 1036383 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1393. Min Act: -0.0001

Data Index: 297316 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1285. Min Act: -0.0001

Data Index: 457505 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1439. Min Act: -0.0001

Data Index: 1328294 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1448. Min Act: -0.0001

Data Index: 1528498 (Python Code)

Max Activating Token Index: 355

Text #11

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1493. Min Act: -0.0001

Data Index: 88116 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1340. Min Act: -0.0001

Data Index: 279541 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1982. Min Act: -0.0001

Data Index: 1240001 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1719. Min Act: -0.0001

Data Index: 1167877 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1526. Min Act: -0.0001

Data Index: 836613 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1411. Min Act: -0.0001

Data Index: 444606 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1501. Min Act: -0.0001

Data Index: 394609 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1460. Min Act: -0.0001

Data Index: 253582 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1444. Min Act: -0.0001

Data Index: 1339240 (C4 (Web Text))

Max Activating Token Index: 294