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

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

Neuron 403 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: 0.2799. Min Range: -0.2799

Max Act: 0.2799. Min Act: -0.0002

Data Index: 1065639 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2796. Min Act: -0.0003

Data Index: 393833 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2709. Min Act: -0.0002

Data Index: 401954 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2342. Min Act: -0.0002

Data Index: 1117714 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2379. Min Act: -0.0002

Data Index: 38297 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2330. Min Act: -0.0002

Data Index: 448871 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2276. Min Act: -0.0002

Data Index: 1220627 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2246. Min Act: -0.0002

Data Index: 1007205 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2220. Min Act: -0.0002

Data Index: 276624 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2241. Min Act: -0.0002

Data Index: 276577 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2185. Min Act: -0.0002

Data Index: 796674 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2160. Min Act: -0.0002

Data Index: 635783 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2142. Min Act: -0.0002

Data Index: 1105630 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2106. Min Act: -0.0002

Data Index: 1262325 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2059. Min Act: -0.0002

Data Index: 91529 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2137. Min Act: -0.0002

Data Index: 146739 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2017. Min Act: -0.0002

Data Index: 953837 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.1965. Min Act: -0.0003

Data Index: 391123 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.1991. Min Act: -0.0002

Data Index: 18646 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2007. Min Act: -0.0002

Data Index: 752296 (C4 (Web Text))

Max Activating Token Index: 304