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

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

Neuron 5947 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3613. Min Range: -3.3613

Max Act: 3.3613. Min Act: -0.0000

Data Index: 743158 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 3.3613. Min Range: -3.3613

Max Act: 3.1797. Min Act: -0.0000

Data Index: 630904 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 3.3613. Min Range: -3.3613

Max Act: 2.6177. Min Act: -0.0000

Data Index: 783886 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 3.3613. Min Range: -3.3613

Max Act: 2.5233. Min Act: -0.0000

Data Index: 877710 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 3.3613. Min Range: -3.3613

Max Act: 2.4708. Min Act: 0.0000

Data Index: 542903 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 3.3613. Min Range: -3.3613

Max Act: 2.2483. Min Act: -0.0000

Data Index: 1049262 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 3.3613. Min Range: -3.3613

Max Act: 2.2162. Min Act: -0.0000

Data Index: 1492586 (Python Code)

Max Activating Token Index: 660

Text #7

Max Range: 3.3613. Min Range: -3.3613

Max Act: 2.3467. Min Act: -0.0000

Data Index: 1213536 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 3.3613. Min Range: -3.3613

Max Act: 2.2305. Min Act: -0.0000

Data Index: 1069797 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 3.3613. Min Range: -3.3613

Max Act: 2.1938. Min Act: -0.0000

Data Index: 1650469 (Python Code)

Max Activating Token Index: 682

Text #10

Max Range: 3.3613. Min Range: -3.3613

Max Act: 2.0578. Min Act: -0.0000

Data Index: 1030320 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 3.3613. Min Range: -3.3613

Max Act: 2.0328. Min Act: -0.0000

Data Index: 370582 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 3.3613. Min Range: -3.3613

Max Act: 1.9205. Min Act: -0.0000

Data Index: 1444892 (Python Code)

Max Activating Token Index: 839

Text #13

Max Range: 3.3613. Min Range: -3.3613

Max Act: 2.1221. Min Act: -0.0000

Data Index: 780255 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 3.3613. Min Range: -3.3613

Max Act: 2.0138. Min Act: -0.0000

Data Index: 270556 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 3.3613. Min Range: -3.3613

Max Act: 2.1017. Min Act: -0.0000

Data Index: 230864 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 3.3613. Min Range: -3.3613

Max Act: 2.0027. Min Act: -0.0000

Data Index: 720646 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 3.3613. Min Range: -3.3613

Max Act: 1.9879. Min Act: -0.0000

Data Index: 645234 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 3.3613. Min Range: -3.3613

Max Act: 1.8755. Min Act: -0.0000

Data Index: 1204287 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 3.3613. Min Range: -3.3613

Max Act: 1.8577. Min Act: -0.0000

Data Index: 698487 (C4 (Web Text))

Max Activating Token Index: 767