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

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

Neuron 1850 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4726. Min Range: -4.4726

Max Act: 4.4726. Min Act: -0.0001

Data Index: 1304969 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 4.4726. Min Range: -4.4726

Max Act: 3.9646. Min Act: -0.0001

Data Index: 967594 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 4.4726. Min Range: -4.4726

Max Act: 3.2655. Min Act: -0.0000

Data Index: 523691 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 4.4726. Min Range: -4.4726

Max Act: 3.4145. Min Act: -0.0001

Data Index: 747653 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 4.4726. Min Range: -4.4726

Max Act: 3.1675. Min Act: -0.0001

Data Index: 523941 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 4.4726. Min Range: -4.4726

Max Act: 3.2808. Min Act: -0.0000

Data Index: 1273753 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 4.4726. Min Range: -4.4726

Max Act: 3.1207. Min Act: -0.0000

Data Index: 799463 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 4.4726. Min Range: -4.4726

Max Act: 2.9929. Min Act: -0.0000

Data Index: 285298 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 4.4726. Min Range: -4.4726

Max Act: 2.9720. Min Act: -0.0000

Data Index: 1348687 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 4.4726. Min Range: -4.4726

Max Act: 2.9635. Min Act: -0.0001

Data Index: 884861 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 4.4726. Min Range: -4.4726

Max Act: 2.7884. Min Act: -0.0000

Data Index: 746340 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 4.4726. Min Range: -4.4726

Max Act: 3.0566. Min Act: -0.0000

Data Index: 965420 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 4.4726. Min Range: -4.4726

Max Act: 2.9064. Min Act: -0.0000

Data Index: 102671 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 4.4726. Min Range: -4.4726

Max Act: 2.9051. Min Act: -0.0001

Data Index: 766236 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 4.4726. Min Range: -4.4726

Max Act: 2.6898. Min Act: -0.0001

Data Index: 1239219 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 4.4726. Min Range: -4.4726

Max Act: 2.6758. Min Act: -0.0000

Data Index: 119148 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 4.4726. Min Range: -4.4726

Max Act: 2.7243. Min Act: -0.0001

Data Index: 250299 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 4.4726. Min Range: -4.4726

Max Act: 2.6800. Min Act: -0.0000

Data Index: 52150 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 4.4726. Min Range: -4.4726

Max Act: 2.6049. Min Act: -0.0000

Data Index: 204523 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 4.4726. Min Range: -4.4726

Max Act: 2.6568. Min Act: -0.0001

Data Index: 1154346 (C4 (Web Text))

Max Activating Token Index: 282