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

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

Neuron 3142 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1756. Min Act: -0.0001

Data Index: 495292 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1798. Min Act: -0.0002

Data Index: 1161764 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1719. Min Act: -0.0001

Data Index: 1135754 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1662. Min Act: -0.0001

Data Index: 959861 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1761. Min Act: -0.0001

Data Index: 718937 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1577. Min Act: -0.0002

Data Index: 356648 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1437. Min Act: -0.0002

Data Index: 1320369 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1595. Min Act: -0.0001

Data Index: 493738 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1535. Min Act: -0.0001

Data Index: 1297959 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1566. Min Act: -0.0001

Data Index: 1442988 (Python Code)

Max Activating Token Index: 17

Text #10

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1499. Min Act: -0.0002

Data Index: 170552 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1550. Min Act: -0.0001

Data Index: 1294821 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1531. Min Act: -0.0002

Data Index: 1012849 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1505. Min Act: -0.0001

Data Index: 948303 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1547. Min Act: -0.0001

Data Index: 1227631 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1500. Min Act: -0.0002

Data Index: 57184 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1420. Min Act: -0.0001

Data Index: 1462917 (Python Code)

Max Activating Token Index: 41

Text #17

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1511. Min Act: -0.0001

Data Index: 392240 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1469. Min Act: -0.0001

Data Index: 840005 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1402. Min Act: -0.0002

Data Index: 1164025 (C4 (Web Text))

Max Activating Token Index: 164