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

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

Neuron 2040 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9870. Min Range: -5.9870

Max Act: 5.8676. Min Act: -0.0000

Data Index: 845172 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 5.9870. Min Range: -5.9870

Max Act: 5.9870. Min Act: -0.0000

Data Index: 356934 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 5.9870. Min Range: -5.9870

Max Act: 5.5221. Min Act: -0.0000

Data Index: 1252485 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 5.9870. Min Range: -5.9870

Max Act: 5.7854. Min Act: -0.0000

Data Index: 538057 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 5.9870. Min Range: -5.9870

Max Act: 5.0713. Min Act: -0.0000

Data Index: 944910 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 5.9870. Min Range: -5.9870

Max Act: 5.7537. Min Act: -0.0000

Data Index: 906907 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 5.9870. Min Range: -5.9870

Max Act: 5.6688. Min Act: -0.0001

Data Index: 414243 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 5.9870. Min Range: -5.9870

Max Act: 5.3108. Min Act: -0.0001

Data Index: 878662 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 5.9870. Min Range: -5.9870

Max Act: 5.0201. Min Act: -0.0000

Data Index: 773783 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 5.9870. Min Range: -5.9870

Max Act: 5.3363. Min Act: -0.0000

Data Index: 1357942 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 5.9870. Min Range: -5.9870

Max Act: 4.9739. Min Act: -0.0001

Data Index: 1159047 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 5.9870. Min Range: -5.9870

Max Act: 4.8587. Min Act: -0.0000

Data Index: 625053 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 5.9870. Min Range: -5.9870

Max Act: 4.7924. Min Act: -0.0000

Data Index: 247957 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 5.9870. Min Range: -5.9870

Max Act: 4.7261. Min Act: -0.0001

Data Index: 35590 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 5.9870. Min Range: -5.9870

Max Act: 4.5292. Min Act: -0.0000

Data Index: 828997 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 5.9870. Min Range: -5.9870

Max Act: 4.5390. Min Act: -0.0000

Data Index: 191167 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 5.9870. Min Range: -5.9870

Max Act: 4.6856. Min Act: -0.0000

Data Index: 97316 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 5.9870. Min Range: -5.9870

Max Act: 4.6829. Min Act: -0.0000

Data Index: 12999 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 5.9870. Min Range: -5.9870

Max Act: 5.0055. Min Act: -0.0000

Data Index: 687732 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 5.9870. Min Range: -5.9870

Max Act: 4.6422. Min Act: -0.0000

Data Index: 115789 (C4 (Web Text))

Max Activating Token Index: 208