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

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

Neuron 3314 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5875. Min Act: -0.0000

Data Index: 188635 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.6307. Min Act: -0.0000

Data Index: 344888 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4823. Min Act: -0.0000

Data Index: 735924 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4874. Min Act: -0.0000

Data Index: 292847 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5006. Min Act: -0.0000

Data Index: 918785 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4899. Min Act: -0.0000

Data Index: 25934 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4675. Min Act: -0.0000

Data Index: 86916 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4795. Min Act: -0.0000

Data Index: 194570 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4554. Min Act: -0.0000

Data Index: 222972 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1278414 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4587. Min Act: -0.0000

Data Index: 1195850 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4495. Min Act: -0.0000

Data Index: 212111 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4315. Min Act: -0.0000

Data Index: 141645 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4307. Min Act: -0.0000

Data Index: 1193290 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4389. Min Act: -0.0000

Data Index: 1256631 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4002. Min Act: -0.0000

Data Index: 748317 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4271. Min Act: -0.0000

Data Index: 132800 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.3963. Min Act: -0.0000

Data Index: 251069 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1335075 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.3902. Min Act: -0.0000

Data Index: 1076116 (C4 (Web Text))

Max Activating Token Index: 96