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

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

Neuron 2802 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7073. Min Range: -4.7073

Max Act: 4.7073. Min Act: -0.0000

Data Index: 107703 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 4.7073. Min Range: -4.7073

Max Act: 3.9432. Min Act: -0.0000

Data Index: 792918 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 4.7073. Min Range: -4.7073

Max Act: 3.7651. Min Act: -0.0000

Data Index: 1248274 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 4.7073. Min Range: -4.7073

Max Act: 4.0433. Min Act: -0.0000

Data Index: 1058936 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 4.7073. Min Range: -4.7073

Max Act: 4.1116. Min Act: -0.0000

Data Index: 689108 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 4.7073. Min Range: -4.7073

Max Act: 3.5483. Min Act: -0.0000

Data Index: 907527 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 4.7073. Min Range: -4.7073

Max Act: 3.3953. Min Act: -0.0000

Data Index: 538850 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 4.7073. Min Range: -4.7073

Max Act: 3.1720. Min Act: -0.0000

Data Index: 1352090 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 4.7073. Min Range: -4.7073

Max Act: 3.1494. Min Act: -0.0000

Data Index: 573488 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 4.7073. Min Range: -4.7073

Max Act: 2.6955. Min Act: -0.0000

Data Index: 573482 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 4.7073. Min Range: -4.7073

Max Act: 2.7219. Min Act: -0.0000

Data Index: 257795 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 4.7073. Min Range: -4.7073

Max Act: 2.6739. Min Act: -0.0000

Data Index: 551100 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 4.7073. Min Range: -4.7073

Max Act: 2.3132. Min Act: -0.0000

Data Index: 639293 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 4.7073. Min Range: -4.7073

Max Act: 2.3283. Min Act: -0.0000

Data Index: 731024 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 4.7073. Min Range: -4.7073

Max Act: 2.3183. Min Act: -0.0000

Data Index: 148204 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 4.7073. Min Range: -4.7073

Max Act: 2.4394. Min Act: -0.0000

Data Index: 528626 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 4.7073. Min Range: -4.7073

Max Act: 2.4195. Min Act: -0.0000

Data Index: 232488 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 4.7073. Min Range: -4.7073

Max Act: 2.3164. Min Act: -0.0000

Data Index: 256445 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 4.7073. Min Range: -4.7073

Max Act: 1.9507. Min Act: -0.0000

Data Index: 797329 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 4.7073. Min Range: -4.7073

Max Act: 2.3718. Min Act: -0.0000

Data Index: 84993 (C4 (Web Text))

Max Activating Token Index: 725