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

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

Neuron 223 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1427304 (Python Code)

Max Activating Token Index: 208

Text #1

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5954. Min Act: -0.0000

Data Index: 731287 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.6026. Min Act: -0.0000

Data Index: 1030805 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5985. Min Act: -0.0000

Data Index: 747677 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5861. Min Act: -0.0000

Data Index: 891272 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1381035 (Python Code)

Max Activating Token Index: 663

Text #6

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1613000 (Python Code)

Max Activating Token Index: 95

Text #7

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5001. Min Act: -0.0000

Data Index: 1643926 (Python Code)

Max Activating Token Index: 71

Text #8

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.4679. Min Act: -0.0000

Data Index: 329842 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5256. Min Act: -0.0000

Data Index: 1597563 (Python Code)

Max Activating Token Index: 168

Text #10

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.4680. Min Act: -0.0000

Data Index: 925453 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.4753. Min Act: -0.0000

Data Index: 271477 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.4581. Min Act: -0.0000

Data Index: 1557184 (Python Code)

Max Activating Token Index: 458

Text #13

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.4702. Min Act: -0.0000

Data Index: 1450828 (Python Code)

Max Activating Token Index: 587

Text #14

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.4481. Min Act: -0.0000

Data Index: 899962 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.4003. Min Act: -0.0000

Data Index: 649059 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.4214. Min Act: -0.0000

Data Index: 1541174 (Python Code)

Max Activating Token Index: 935

Text #17

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.4291. Min Act: -0.0000

Data Index: 1647479 (Python Code)

Max Activating Token Index: 596

Text #18

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1584567 (Python Code)

Max Activating Token Index: 875

Text #19

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.3896. Min Act: -0.0000

Data Index: 1585847 (Python Code)

Max Activating Token Index: 570