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

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

Neuron 4177 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4717. Min Range: -3.4717

Max Act: 3.4717. Min Act: -0.0002

Data Index: 685641 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.8634. Min Act: -0.0002

Data Index: 95435 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.9434. Min Act: -0.0002

Data Index: 892565 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 3.4717. Min Range: -3.4717

Max Act: 3.0730. Min Act: -0.0002

Data Index: 1161131 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 3.4717. Min Range: -3.4717

Max Act: 3.2487. Min Act: -0.0002

Data Index: 331630 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.9881. Min Act: -0.0002

Data Index: 1350720 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.9132. Min Act: -0.0002

Data Index: 699954 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.8277. Min Act: -0.0002

Data Index: 506813 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 3.4717. Min Range: -3.4717

Max Act: 3.2897. Min Act: -0.0002

Data Index: 1143140 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 3.4717. Min Range: -3.4717

Max Act: 3.2852. Min Act: -0.0002

Data Index: 680615 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.7647. Min Act: -0.0002

Data Index: 548104 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.7908. Min Act: -0.0002

Data Index: 1203765 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.6133. Min Act: -0.0002

Data Index: 1321256 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.9525. Min Act: -0.0002

Data Index: 1132360 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 3.4717. Min Range: -3.4717

Max Act: 3.1004. Min Act: -0.0002

Data Index: 481962 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.9687. Min Act: -0.0002

Data Index: 768565 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.9503. Min Act: -0.0002

Data Index: 932564 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.5504. Min Act: -0.0002

Data Index: 243511 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.8369. Min Act: -0.0002

Data Index: 405083 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 3.4717. Min Range: -3.4717

Max Act: 2.9386. Min Act: -0.0002

Data Index: 1189657 (C4 (Web Text))

Max Activating Token Index: 136