Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2399 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0415. Min Range: -2.0415

Max Act: 2.0415. Min Act: -0.0000

Data Index: 752735 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 2.0415. Min Range: -2.0415

Max Act: 1.7221. Min Act: -0.0000

Data Index: 123882 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 2.0415. Min Range: -2.0415

Max Act: 1.7814. Min Act: -0.0000

Data Index: 836490 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 2.0415. Min Range: -2.0415

Max Act: 1.5358. Min Act: -0.0000

Data Index: 867082 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 2.0415. Min Range: -2.0415

Max Act: 1.6185. Min Act: -0.0000

Data Index: 109182 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 2.0415. Min Range: -2.0415

Max Act: 1.4005. Min Act: -0.0000

Data Index: 193446 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 2.0415. Min Range: -2.0415

Max Act: 1.4843. Min Act: -0.0000

Data Index: 282227 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 2.0415. Min Range: -2.0415

Max Act: 1.4520. Min Act: -0.0000

Data Index: 223422 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 2.0415. Min Range: -2.0415

Max Act: 1.4077. Min Act: -0.0000

Data Index: 661230 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 2.0415. Min Range: -2.0415

Max Act: 1.4044. Min Act: -0.0000

Data Index: 1288856 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 2.0415. Min Range: -2.0415

Max Act: 1.3850. Min Act: -0.0000

Data Index: 1321802 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 2.0415. Min Range: -2.0415

Max Act: 1.3762. Min Act: -0.0000

Data Index: 1064688 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 2.0415. Min Range: -2.0415

Max Act: 1.3667. Min Act: -0.0000

Data Index: 286547 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 2.0415. Min Range: -2.0415

Max Act: 1.3403. Min Act: -0.0000

Data Index: 1142922 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 2.0415. Min Range: -2.0415

Max Act: 1.3265. Min Act: -0.0000

Data Index: 440921 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 2.0415. Min Range: -2.0415

Max Act: 1.2980. Min Act: -0.0000

Data Index: 688696 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 2.0415. Min Range: -2.0415

Max Act: 1.2912. Min Act: -0.0000

Data Index: 243413 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 2.0415. Min Range: -2.0415

Max Act: 1.2092. Min Act: -0.0000

Data Index: 478655 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 2.0415. Min Range: -2.0415

Max Act: 1.2721. Min Act: -0.0000

Data Index: 700482 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 2.0415. Min Range: -2.0415

Max Act: 1.1951. Min Act: -0.0000

Data Index: 389454 (C4 (Web Text))

Max Activating Token Index: 450