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

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

Neuron 3905 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9978. Min Range: -5.9978

Max Act: 5.8240. Min Act: -0.0000

Data Index: 192816 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 5.9978. Min Range: -5.9978

Max Act: 5.9978. Min Act: -0.0000

Data Index: 263898 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 5.9978. Min Range: -5.9978

Max Act: 5.5714. Min Act: -0.0000

Data Index: 930775 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 5.9978. Min Range: -5.9978

Max Act: 5.9410. Min Act: -0.0000

Data Index: 603899 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 5.9978. Min Range: -5.9978

Max Act: 5.2992. Min Act: -0.0000

Data Index: 35684 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 5.9978. Min Range: -5.9978

Max Act: 5.3095. Min Act: -0.0000

Data Index: 672518 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 5.9978. Min Range: -5.9978

Max Act: 5.2734. Min Act: -0.0000

Data Index: 1112829 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 5.9978. Min Range: -5.9978

Max Act: 5.0723. Min Act: -0.0000

Data Index: 939534 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 5.9978. Min Range: -5.9978

Max Act: 4.9938. Min Act: -0.0000

Data Index: 709972 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 5.9978. Min Range: -5.9978

Max Act: 4.4433. Min Act: -0.0000

Data Index: 153988 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 5.9978. Min Range: -5.9978

Max Act: 4.8401. Min Act: -0.0000

Data Index: 513871 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 5.9978. Min Range: -5.9978

Max Act: 4.4700. Min Act: -0.0000

Data Index: 1569184 (Python Code)

Max Activating Token Index: 922

Text #12

Max Range: 5.9978. Min Range: -5.9978

Max Act: 4.6496. Min Act: -0.0000

Data Index: 324378 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 5.9978. Min Range: -5.9978

Max Act: 4.6086. Min Act: -0.0000

Data Index: 1069841 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 5.9978. Min Range: -5.9978

Max Act: 4.6524. Min Act: -0.0000

Data Index: 707354 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 5.9978. Min Range: -5.9978

Max Act: 4.3338. Min Act: -0.0000

Data Index: 1580789 (Python Code)

Max Activating Token Index: 168

Text #16

Max Range: 5.9978. Min Range: -5.9978

Max Act: 4.2738. Min Act: -0.0000

Data Index: 678367 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 5.9978. Min Range: -5.9978

Max Act: 4.2506. Min Act: -0.0000

Data Index: 563446 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 5.9978. Min Range: -5.9978

Max Act: 4.4130. Min Act: -0.0000

Data Index: 301260 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 5.9978. Min Range: -5.9978

Max Act: 4.2491. Min Act: -0.0000

Data Index: 760587 (C4 (Web Text))

Max Activating Token Index: 482