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

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

Neuron 737 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.8473. Min Act: -0.0000

Data Index: 543966 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.8187. Min Act: -0.0000

Data Index: 900571 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.8196. Min Act: -0.0000

Data Index: 283844 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.7700. Min Act: -0.0000

Data Index: 220190 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.7394. Min Act: -0.0000

Data Index: 448337 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.7522. Min Act: -0.0000

Data Index: 240692 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.6771. Min Act: -0.0000

Data Index: 553432 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.7033. Min Act: -0.0000

Data Index: 938031 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.6553. Min Act: -0.0000

Data Index: 1021184 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.6674. Min Act: -0.0000

Data Index: 798506 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1089359 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.6404. Min Act: -0.0000

Data Index: 320935 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.6462. Min Act: -0.0000

Data Index: 460584 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.6468. Min Act: -0.0000

Data Index: 1087210 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.5624. Min Act: -0.0000

Data Index: 960467 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1312967 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.5035. Min Act: -0.0000

Data Index: 437966 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.5279. Min Act: -0.0000

Data Index: 398097 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.5293. Min Act: 0.0000

Data Index: 731380 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.4822. Min Act: -0.0000

Data Index: 26257 (C4 (Web Text))

Max Activating Token Index: 404