Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 985 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1509927 (Python Code)

Max Activating Token Index: 225

Text #1

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1400381 (Python Code)

Max Activating Token Index: 816

Text #2

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5640. Min Act: -0.0000

Data Index: 1262341 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5547. Min Act: -0.0000

Data Index: 1401261 (Python Code)

Max Activating Token Index: 1021

Text #4

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5406. Min Act: -0.0000

Data Index: 1571217 (Python Code)

Max Activating Token Index: 424

Text #5

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4521. Min Act: -0.0000

Data Index: 108140 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4580. Min Act: -0.0000

Data Index: 1617671 (Python Code)

Max Activating Token Index: 95

Text #7

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1445270 (Python Code)

Max Activating Token Index: 404

Text #8

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4534. Min Act: -0.0000

Data Index: 813573 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4510. Min Act: -0.0000

Data Index: 1471636 (Python Code)

Max Activating Token Index: 239

Text #10

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4157. Min Act: -0.0000

Data Index: 1640979 (Python Code)

Max Activating Token Index: 544

Text #11

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1492935 (Python Code)

Max Activating Token Index: 66

Text #12

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1624327 (Python Code)

Max Activating Token Index: 683

Text #13

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1455903 (Python Code)

Max Activating Token Index: 627

Text #14

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1113466 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4039. Min Act: -0.0000

Data Index: 1530543 (Python Code)

Max Activating Token Index: 193

Text #16

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4169. Min Act: -0.0000

Data Index: 1419229 (Python Code)

Max Activating Token Index: 389

Text #17

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1363381 (Python Code)

Max Activating Token Index: 623

Text #18

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4036. Min Act: -0.0000

Data Index: 1488368 (Python Code)

Max Activating Token Index: 201

Text #19

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4133. Min Act: -0.0000

Data Index: 1575793 (Python Code)

Max Activating Token Index: 91