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

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

Neuron 5699 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1692. Min Range: -4.1692

Max Act: 4.0574. Min Act: -0.0000

Data Index: 1246787 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 4.1692. Min Range: -4.1692

Max Act: 4.1692. Min Act: -0.0000

Data Index: 963544 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 4.1692. Min Range: -4.1692

Max Act: 4.0249. Min Act: -0.0000

Data Index: 351469 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 4.1692. Min Range: -4.1692

Max Act: 3.8389. Min Act: -0.0000

Data Index: 784163 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 4.1692. Min Range: -4.1692

Max Act: 3.5410. Min Act: -0.0000

Data Index: 72876 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 4.1692. Min Range: -4.1692

Max Act: 3.4950. Min Act: -0.0000

Data Index: 363677 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 4.1692. Min Range: -4.1692

Max Act: 3.4510. Min Act: -0.0000

Data Index: 308265 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 4.1692. Min Range: -4.1692

Max Act: 3.6042. Min Act: -0.0000

Data Index: 610111 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 4.1692. Min Range: -4.1692

Max Act: 3.5457. Min Act: -0.0000

Data Index: 1261862 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 4.1692. Min Range: -4.1692

Max Act: 3.2982. Min Act: -0.0000

Data Index: 1189550 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 4.1692. Min Range: -4.1692

Max Act: 3.0375. Min Act: -0.0000

Data Index: 1007181 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 4.1692. Min Range: -4.1692

Max Act: 3.3658. Min Act: -0.0000

Data Index: 619742 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 4.1692. Min Range: -4.1692

Max Act: 3.3009. Min Act: -0.0000

Data Index: 546915 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 4.1692. Min Range: -4.1692

Max Act: 2.9196. Min Act: -0.0000

Data Index: 516143 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 4.1692. Min Range: -4.1692

Max Act: 2.8473. Min Act: -0.0000

Data Index: 39066 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 4.1692. Min Range: -4.1692

Max Act: 2.8460. Min Act: -0.0000

Data Index: 1069210 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 4.1692. Min Range: -4.1692

Max Act: 2.8075. Min Act: -0.0000

Data Index: 1080887 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 4.1692. Min Range: -4.1692

Max Act: 2.7693. Min Act: -0.0000

Data Index: 1323749 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 4.1692. Min Range: -4.1692

Max Act: 2.6859. Min Act: -0.0000

Data Index: 545600 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 4.1692. Min Range: -4.1692

Max Act: 2.5434. Min Act: -0.0000

Data Index: 466891 (C4 (Web Text))

Max Activating Token Index: 236