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

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

Neuron 1531 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: 1.3828. Min Range: -1.3828

Max Act: 1.3828. Min Act: -0.0002

Data Index: 618923 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 1.3828. Min Range: -1.3828

Max Act: 1.3601. Min Act: -0.0002

Data Index: 399935 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 1.3828. Min Range: -1.3828

Max Act: 1.3524. Min Act: -0.0002

Data Index: 165650 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 1.3828. Min Range: -1.3828

Max Act: 1.3207. Min Act: -0.0002

Data Index: 866790 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 1.3828. Min Range: -1.3828

Max Act: 1.2986. Min Act: -0.0002

Data Index: 1091178 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 1.3828. Min Range: -1.3828

Max Act: 1.2942. Min Act: -0.0002

Data Index: 1121403 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 1.3828. Min Range: -1.3828

Max Act: 1.2672. Min Act: -0.0002

Data Index: 846091 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 1.3828. Min Range: -1.3828

Max Act: 1.2498. Min Act: -0.0002

Data Index: 1241159 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 1.3828. Min Range: -1.3828

Max Act: 1.2655. Min Act: -0.0002

Data Index: 798754 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 1.3828. Min Range: -1.3828

Max Act: 1.2438. Min Act: -0.0002

Data Index: 74071 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 1.3828. Min Range: -1.3828

Max Act: 1.2697. Min Act: -0.0002

Data Index: 830138 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 1.3828. Min Range: -1.3828

Max Act: 1.2402. Min Act: -0.0002

Data Index: 943728 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 1.3828. Min Range: -1.3828

Max Act: 1.2242. Min Act: -0.0002

Data Index: 947209 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 1.3828. Min Range: -1.3828

Max Act: 1.2119. Min Act: -0.0002

Data Index: 249693 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 1.3828. Min Range: -1.3828

Max Act: 1.2145. Min Act: -0.0002

Data Index: 1164543 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 1.3828. Min Range: -1.3828

Max Act: 1.2041. Min Act: -0.0002

Data Index: 620841 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 1.3828. Min Range: -1.3828

Max Act: 1.2374. Min Act: -0.0002

Data Index: 700304 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 1.3828. Min Range: -1.3828

Max Act: 1.2180. Min Act: -0.0002

Data Index: 912734 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 1.3828. Min Range: -1.3828

Max Act: 1.2020. Min Act: -0.0002

Data Index: 272825 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 1.3828. Min Range: -1.3828

Max Act: 1.1734. Min Act: -0.0002

Data Index: 829847 (C4 (Web Text))

Max Activating Token Index: 755