Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4049 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.0712. Min Range: -4.0712

Max Act: 4.0712. Min Act: -0.0000

Data Index: 908720 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.7296. Min Act: -0.0000

Data Index: 147982 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.8673. Min Act: -0.0000

Data Index: 203608 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.6629. Min Act: -0.0000

Data Index: 1310077 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.5032. Min Act: -0.0000

Data Index: 1224230 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.6201. Min Act: -0.0000

Data Index: 448130 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.7610. Min Act: -0.0000

Data Index: 548475 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.7132. Min Act: -0.0000

Data Index: 607713 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.4174. Min Act: -0.0000

Data Index: 330003 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.5315. Min Act: -0.0000

Data Index: 334586 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 4.0712. Min Range: -4.0712

Max Act: 2.9394. Min Act: -0.0000

Data Index: 966645 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.6514. Min Act: -0.0000

Data Index: 55893 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.4422. Min Act: -0.0000

Data Index: 259154 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.2812. Min Act: -0.0000

Data Index: 1172082 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.2531. Min Act: -0.0000

Data Index: 653782 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.5832. Min Act: -0.0000

Data Index: 1258786 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.2404. Min Act: -0.0000

Data Index: 492265 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.3726. Min Act: -0.0000

Data Index: 755317 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.3958. Min Act: -0.0000

Data Index: 714550 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 4.0712. Min Range: -4.0712

Max Act: 3.3707. Min Act: -0.0000

Data Index: 767848 (C4 (Web Text))

Max Activating Token Index: 89