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

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

Neuron 156 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.7443. Min Act: -0.0000

Data Index: 950917 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.6671. Min Act: -0.0000

Data Index: 1005634 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.5357. Min Act: -0.0000

Data Index: 123501 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.3606. Min Act: -0.0000

Data Index: 814664 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.3157. Min Act: -0.0000

Data Index: 82584 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.3172. Min Act: -0.0000

Data Index: 1058925 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.2978. Min Act: -0.0000

Data Index: 290324 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.1866. Min Act: -0.0000

Data Index: 926763 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.1537. Min Act: -0.0000

Data Index: 712802 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.1144. Min Act: -0.0000

Data Index: 907682 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.0726. Min Act: -0.0000

Data Index: 144896 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.2071. Min Act: -0.0000

Data Index: 252143 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.2237. Min Act: -0.0000

Data Index: 281627 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.2373. Min Act: -0.0000

Data Index: 291495 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.1596. Min Act: -0.0000

Data Index: 685004 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.1159. Min Act: -0.0000

Data Index: 1081492 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.1949. Min Act: -0.0000

Data Index: 152020 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.1378. Min Act: -0.0000

Data Index: 43763 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.2723. Min Act: -0.0000

Data Index: 324478 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.1512. Min Act: -0.0000

Data Index: 55380 (C4 (Web Text))

Max Activating Token Index: 474