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

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

Neuron 4393 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.2085. Min Act: -0.0000

Data Index: 793116 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.2052. Min Act: -0.0000

Data Index: 410653 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1858. Min Act: -0.0000

Data Index: 621189 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1766. Min Act: -0.0000

Data Index: 626316 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1858. Min Act: -0.0000

Data Index: 76691 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1637. Min Act: -0.0000

Data Index: 1000329 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1645. Min Act: -0.0000

Data Index: 594400 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1565. Min Act: -0.0000

Data Index: 1062605 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1549. Min Act: -0.0000

Data Index: 667739 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1481. Min Act: -0.0000

Data Index: 1458706 (Python Code)

Max Activating Token Index: 667

Text #10

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1469. Min Act: -0.0000

Data Index: 996676 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1525. Min Act: -0.0000

Data Index: 1491796 (Python Code)

Max Activating Token Index: 814

Text #12

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1523. Min Act: -0.0000

Data Index: 489824 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1401955 (Python Code)

Max Activating Token Index: 645

Text #14

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1511. Min Act: -0.0000

Data Index: 574858 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1555. Min Act: -0.0000

Data Index: 583741 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1493. Min Act: -0.0000

Data Index: 74148 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1439. Min Act: -0.0000

Data Index: 198199 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1431. Min Act: -0.0000

Data Index: 301701 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1367. Min Act: -0.0000

Data Index: 997940 (C4 (Web Text))

Max Activating Token Index: 489