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

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

Neuron 1741 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: 2.6403. Min Range: -2.6403

Max Act: 2.6403. Min Act: -0.0000

Data Index: 1589480 (Python Code)

Max Activating Token Index: 539

Text #1

Max Range: 2.6403. Min Range: -2.6403

Max Act: 2.4751. Min Act: -0.0000

Data Index: 1370748 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 2.6403. Min Range: -2.6403

Max Act: 2.0033. Min Act: -0.0000

Data Index: 1442874 (Python Code)

Max Activating Token Index: 197

Text #3

Max Range: 2.6403. Min Range: -2.6403

Max Act: 2.2117. Min Act: -0.0000

Data Index: 1534498 (Python Code)

Max Activating Token Index: 248

Text #4

Max Range: 2.6403. Min Range: -2.6403

Max Act: 2.2761. Min Act: -0.0000

Data Index: 1598997 (Python Code)

Max Activating Token Index: 473

Text #5

Max Range: 2.6403. Min Range: -2.6403

Max Act: 2.1471. Min Act: -0.0000

Data Index: 1602986 (Python Code)

Max Activating Token Index: 12

Text #6

Max Range: 2.6403. Min Range: -2.6403

Max Act: 2.4828. Min Act: -0.0000

Data Index: 1434107 (Python Code)

Max Activating Token Index: 66

Text #7

Max Range: 2.6403. Min Range: -2.6403

Max Act: 2.2526. Min Act: -0.0000

Data Index: 1592947 (Python Code)

Max Activating Token Index: 886

Text #8

Max Range: 2.6403. Min Range: -2.6403

Max Act: 2.1124. Min Act: -0.0000

Data Index: 1645151 (Python Code)

Max Activating Token Index: 692

Text #9

Max Range: 2.6403. Min Range: -2.6403

Max Act: 2.1767. Min Act: -0.0000

Data Index: 1606929 (Python Code)

Max Activating Token Index: 139

Text #10

Max Range: 2.6403. Min Range: -2.6403

Max Act: 2.0374. Min Act: -0.0000

Data Index: 1529711 (Python Code)

Max Activating Token Index: 795

Text #11

Max Range: 2.6403. Min Range: -2.6403

Max Act: 2.1726. Min Act: -0.0000

Data Index: 1656608 (Python Code)

Max Activating Token Index: 155

Text #12

Max Range: 2.6403. Min Range: -2.6403

Max Act: 2.2579. Min Act: -0.0000

Data Index: 1431297 (Python Code)

Max Activating Token Index: 642

Text #13

Max Range: 2.6403. Min Range: -2.6403

Max Act: 2.1513. Min Act: -0.0000

Data Index: 1388345 (Python Code)

Max Activating Token Index: 543

Text #14

Max Range: 2.6403. Min Range: -2.6403

Max Act: 1.9207. Min Act: -0.0000

Data Index: 1543643 (Python Code)

Max Activating Token Index: 562

Text #15

Max Range: 2.6403. Min Range: -2.6403

Max Act: 2.2191. Min Act: -0.0000

Data Index: 644237 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 2.6403. Min Range: -2.6403

Max Act: 2.0635. Min Act: -0.0000

Data Index: 1532078 (Python Code)

Max Activating Token Index: 44

Text #17

Max Range: 2.6403. Min Range: -2.6403

Max Act: 1.9040. Min Act: -0.0000

Data Index: 932681 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 2.6403. Min Range: -2.6403

Max Act: 1.7057. Min Act: -0.0000

Data Index: 1408782 (Python Code)

Max Activating Token Index: 839

Text #19

Max Range: 2.6403. Min Range: -2.6403

Max Act: 1.7742. Min Act: -0.0000

Data Index: 1505686 (Python Code)

Max Activating Token Index: 945