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

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

Neuron 2362 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.2711. Min Act: -0.0001

Data Index: 1430647 (Python Code)

Max Activating Token Index: 462

Text #1

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.0646. Min Act: -0.0001

Data Index: 1494563 (Python Code)

Max Activating Token Index: 523

Text #2

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.0876. Min Act: -0.0001

Data Index: 1588892 (Python Code)

Max Activating Token Index: 945

Text #3

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.0633. Min Act: -0.0001

Data Index: 1561062 (Python Code)

Max Activating Token Index: 132

Text #4

Max Range: 4.2711. Min Range: -4.2711

Max Act: 3.5415. Min Act: -0.0000

Data Index: 30370 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 4.2711. Min Range: -4.2711

Max Act: 3.3937. Min Act: -0.0000

Data Index: 519469 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 4.2711. Min Range: -4.2711

Max Act: 3.3744. Min Act: -0.0001

Data Index: 889272 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 4.2711. Min Range: -4.2711

Max Act: 3.3154. Min Act: -0.0001

Data Index: 421989 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 4.2711. Min Range: -4.2711

Max Act: 3.4224. Min Act: -0.0000

Data Index: 1116407 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 4.2711. Min Range: -4.2711

Max Act: 3.2931. Min Act: -0.0001

Data Index: 1472232 (Python Code)

Max Activating Token Index: 591

Text #10

Max Range: 4.2711. Min Range: -4.2711

Max Act: 3.2982. Min Act: -0.0001

Data Index: 1364132 (Python Code)

Max Activating Token Index: 144

Text #11

Max Range: 4.2711. Min Range: -4.2711

Max Act: 3.3415. Min Act: -0.0001

Data Index: 1562794 (Python Code)

Max Activating Token Index: 578

Text #12

Max Range: 4.2711. Min Range: -4.2711

Max Act: 3.1273. Min Act: -0.0001

Data Index: 1464302 (Python Code)

Max Activating Token Index: 899

Text #13

Max Range: 4.2711. Min Range: -4.2711

Max Act: 2.9790. Min Act: -0.0001

Data Index: 635014 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 4.2711. Min Range: -4.2711

Max Act: 3.1181. Min Act: -0.0001

Data Index: 1507054 (Python Code)

Max Activating Token Index: 294

Text #15

Max Range: 4.2711. Min Range: -4.2711

Max Act: 3.1076. Min Act: -0.0001

Data Index: 982220 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 4.2711. Min Range: -4.2711

Max Act: 3.1006. Min Act: -0.0001

Data Index: 1424576 (Python Code)

Max Activating Token Index: 521

Text #17

Max Range: 4.2711. Min Range: -4.2711

Max Act: 3.2541. Min Act: -0.0000

Data Index: 1111492 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 4.2711. Min Range: -4.2711

Max Act: 3.0770. Min Act: -0.0001

Data Index: 1598567 (Python Code)

Max Activating Token Index: 610

Text #19

Max Range: 4.2711. Min Range: -4.2711

Max Act: 3.3869. Min Act: -0.0001

Data Index: 844155 (C4 (Web Text))

Max Activating Token Index: 880