Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 12 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.6037. Min Act: -0.0001

Data Index: 1110813 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5824. Min Act: -0.0000

Data Index: 959195 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5701. Min Act: -0.0000

Data Index: 474659 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5463. Min Act: 0.0000

Data Index: 156340 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5402. Min Act: 0.0000

Data Index: 608099 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5397. Min Act: -0.0000

Data Index: 1307731 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5469. Min Act: -0.0000

Data Index: 451494 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5212. Min Act: -0.0000

Data Index: 738836 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5085. Min Act: -0.0001

Data Index: 925695 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4936. Min Act: -0.0000

Data Index: 41600 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4956. Min Act: -0.0001

Data Index: 973816 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4715. Min Act: -0.0000

Data Index: 747260 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4858. Min Act: -0.0000

Data Index: 872848 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4654. Min Act: -0.0001

Data Index: 947530 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4666. Min Act: -0.0001

Data Index: 519817 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4696. Min Act: -0.0001

Data Index: 812900 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4507. Min Act: -0.0000

Data Index: 924830 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4581. Min Act: -0.0000

Data Index: 133379 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4566. Min Act: -0.0001

Data Index: 595763 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4415. Min Act: -0.0001

Data Index: 1085060 (C4 (Web Text))

Max Activating Token Index: 134