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

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

Neuron 5408 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: 2.2909. Min Range: -2.2909

Max Act: 2.2909. Min Act: -0.0002

Data Index: 281972 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.2610. Min Act: -0.0002

Data Index: 878802 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.2840. Min Act: -0.0002

Data Index: 2378 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.2661. Min Act: -0.0002

Data Index: 618447 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.2061. Min Act: -0.0002

Data Index: 625717 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.1705. Min Act: -0.0002

Data Index: 404768 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.1567. Min Act: -0.0002

Data Index: 249872 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.1440. Min Act: -0.0002

Data Index: 71462 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.0373. Min Act: -0.0002

Data Index: 544850 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 2.2909. Min Range: -2.2909

Max Act: 1.9882. Min Act: -0.0002

Data Index: 479007 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.0221. Min Act: -0.0003

Data Index: 1312296 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 2.2909. Min Range: -2.2909

Max Act: 1.9060. Min Act: -0.0002

Data Index: 644706 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 2.2909. Min Range: -2.2909

Max Act: 1.9165. Min Act: -0.0002

Data Index: 1063860 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 2.2909. Min Range: -2.2909

Max Act: 1.9420. Min Act: -0.0002

Data Index: 526817 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 2.2909. Min Range: -2.2909

Max Act: 1.8778. Min Act: -0.0002

Data Index: 649585 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 2.2909. Min Range: -2.2909

Max Act: 1.9061. Min Act: -0.0002

Data Index: 802 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 2.2909. Min Range: -2.2909

Max Act: 1.9462. Min Act: -0.0002

Data Index: 457297 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 2.2909. Min Range: -2.2909

Max Act: 1.9258. Min Act: -0.0002

Data Index: 337229 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 2.2909. Min Range: -2.2909

Max Act: 1.8792. Min Act: -0.0002

Data Index: 1008021 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 2.2909. Min Range: -2.2909

Max Act: 1.8144. Min Act: -0.0002

Data Index: 683306 (C4 (Web Text))

Max Activating Token Index: 819