Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2582 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1749. Min Act: -0.0001

Data Index: 1156519 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1632. Min Act: -0.0001

Data Index: 1193875 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1554. Min Act: -0.0001

Data Index: 449984 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1468. Min Act: -0.0001

Data Index: 1268986 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1598. Min Act: -0.0001

Data Index: 638015 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1509. Min Act: -0.0001

Data Index: 177389 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1452. Min Act: -0.0001

Data Index: 1045582 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1482. Min Act: -0.0001

Data Index: 46162 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1536. Min Act: -0.0001

Data Index: 347238 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1539. Min Act: -0.0001

Data Index: 1166201 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1491. Min Act: -0.0001

Data Index: 861198 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1466. Min Act: -0.0001

Data Index: 1015394 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1559. Min Act: -0.0001

Data Index: 403654 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1498. Min Act: -0.0001

Data Index: 309370 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1616. Min Act: -0.0001

Data Index: 506278 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1496. Min Act: -0.0001

Data Index: 1214513 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1483. Min Act: -0.0001

Data Index: 674427 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1490. Min Act: -0.0001

Data Index: 1051635 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1419. Min Act: -0.0001

Data Index: 889652 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1461. Min Act: -0.0001

Data Index: 221078 (C4 (Web Text))

Max Activating Token Index: 129