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

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

Neuron 3257 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2861. Min Act: -0.0001

Data Index: 675347 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2910. Min Act: -0.0001

Data Index: 389447 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2750. Min Act: -0.0001

Data Index: 317546 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2521. Min Act: -0.0001

Data Index: 525895 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2378. Min Act: -0.0001

Data Index: 1345774 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2537. Min Act: -0.0001

Data Index: 1012843 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2553. Min Act: -0.0001

Data Index: 538617 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2585. Min Act: -0.0001

Data Index: 541862 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2809. Min Act: -0.0001

Data Index: 1060212 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2248. Min Act: -0.0001

Data Index: 223034 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2515. Min Act: -0.0001

Data Index: 20322 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2566. Min Act: -0.0001

Data Index: 274815 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2540. Min Act: -0.0001

Data Index: 1124209 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2515. Min Act: -0.0001

Data Index: 204379 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2449. Min Act: -0.0001

Data Index: 484227 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2349. Min Act: -0.0001

Data Index: 889498 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2404. Min Act: -0.0001

Data Index: 164403 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2353. Min Act: -0.0001

Data Index: 740483 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2411. Min Act: -0.0001

Data Index: 1306715 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2402. Min Act: -0.0001

Data Index: 1024455 (C4 (Web Text))

Max Activating Token Index: 775