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

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

Neuron 840 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2696. Min Act: -0.0001

Data Index: 604850 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2410. Min Act: -0.0000

Data Index: 954821 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2461. Min Act: -0.0001

Data Index: 194454 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2157. Min Act: -0.0001

Data Index: 857250 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1541302 (Python Code)

Max Activating Token Index: 691

Text #5

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2067. Min Act: -0.0001

Data Index: 1152705 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1940. Min Act: -0.0001

Data Index: 335794 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1786. Min Act: -0.0000

Data Index: 1431024 (Python Code)

Max Activating Token Index: 652

Text #8

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1864. Min Act: -0.0001

Data Index: 928866 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1755. Min Act: -0.0000

Data Index: 1653768 (Python Code)

Max Activating Token Index: 898

Text #10

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1806. Min Act: -0.0000

Data Index: 1591102 (Python Code)

Max Activating Token Index: 241

Text #11

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1764. Min Act: -0.0001

Data Index: 1347743 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1663. Min Act: -0.0000

Data Index: 1444298 (Python Code)

Max Activating Token Index: 574

Text #13

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1782. Min Act: -0.0001

Data Index: 784150 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1664. Min Act: -0.0000

Data Index: 1531655 (Python Code)

Max Activating Token Index: 578

Text #15

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1761. Min Act: -0.0001

Data Index: 1426292 (Python Code)

Max Activating Token Index: 839

Text #16

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1430338 (Python Code)

Max Activating Token Index: 403

Text #17

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1748. Min Act: -0.0001

Data Index: 1421082 (Python Code)

Max Activating Token Index: 804

Text #18

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1688. Min Act: -0.0001

Data Index: 421817 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1362889 (Python Code)

Max Activating Token Index: 883