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

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

Neuron 3873 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8994. Min Act: -0.0002

Data Index: 95337 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8730. Min Act: -0.0002

Data Index: 92569 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8601. Min Act: -0.0002

Data Index: 1215452 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8483. Min Act: -0.0002

Data Index: 863281 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8213. Min Act: -0.0002

Data Index: 989002 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8185. Min Act: -0.0002

Data Index: 134923 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8157. Min Act: -0.0002

Data Index: 1270727 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8184. Min Act: -0.0002

Data Index: 397639 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8241. Min Act: -0.0002

Data Index: 50698 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8053. Min Act: -0.0002

Data Index: 215238 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.7996. Min Act: -0.0002

Data Index: 1175040 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8018. Min Act: -0.0002

Data Index: 169215 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8039. Min Act: -0.0002

Data Index: 795825 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.7959. Min Act: -0.0002

Data Index: 849312 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8069. Min Act: -0.0002

Data Index: 687666 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.7968. Min Act: -0.0002

Data Index: 178932 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8132. Min Act: -0.0002

Data Index: 1005146 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8137. Min Act: -0.0002

Data Index: 1000407 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8093. Min Act: -0.0002

Data Index: 779684 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.7850. Min Act: -0.0003

Data Index: 453497 (C4 (Web Text))

Max Activating Token Index: 1000