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

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

Neuron 106 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: 0.3287. Min Range: -0.3287

Max Act: 0.3287. Min Act: -0.0000

Data Index: 446948 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.3144. Min Act: -0.0000

Data Index: 216905 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2927. Min Act: -0.0000

Data Index: 1168484 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2823. Min Act: -0.0000

Data Index: 452862 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2619. Min Act: -0.0000

Data Index: 624128 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2755. Min Act: -0.0000

Data Index: 728544 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2659. Min Act: -0.0000

Data Index: 957810 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2682. Min Act: -0.0000

Data Index: 1275548 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2659. Min Act: -0.0000

Data Index: 349442 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1155718 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1274499 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2359. Min Act: -0.0000

Data Index: 190280 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2354. Min Act: -0.0000

Data Index: 639121 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2112. Min Act: -0.0001

Data Index: 375977 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2398. Min Act: -0.0000

Data Index: 731856 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2041. Min Act: -0.0000

Data Index: 767439 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2255. Min Act: -0.0000

Data Index: 226024 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.1989. Min Act: -0.0000

Data Index: 1188132 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2285. Min Act: -0.0000

Data Index: 448512 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1099664 (C4 (Web Text))

Max Activating Token Index: 528