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

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

Neuron 1017 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1398. Min Range: -1.1398

Max Act: 1.1398. Min Act: -0.0001

Data Index: 303981 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.8623. Min Act: -0.0002

Data Index: 1208243 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.8524. Min Act: -0.0001

Data Index: 917910 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.8651. Min Act: -0.0001

Data Index: 856944 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.8667. Min Act: -0.0001

Data Index: 187013 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.7672. Min Act: -0.0001

Data Index: 778778 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.6683. Min Act: -0.0001

Data Index: 288432 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.7039. Min Act: -0.0001

Data Index: 583951 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.6896. Min Act: -0.0001

Data Index: 953799 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.7108. Min Act: -0.0001

Data Index: 740643 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.6828. Min Act: -0.0001

Data Index: 1006201 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.6262. Min Act: -0.0001

Data Index: 606174 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.6469. Min Act: -0.0001

Data Index: 839468 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.6287. Min Act: -0.0002

Data Index: 686704 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.6634. Min Act: -0.0001

Data Index: 1218269 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.6762. Min Act: -0.0002

Data Index: 518389 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.6322. Min Act: -0.0001

Data Index: 768160 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.5994. Min Act: -0.0001

Data Index: 1255111 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.6762. Min Act: -0.0001

Data Index: 765510 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.6100. Min Act: -0.0002

Data Index: 1089105 (C4 (Web Text))

Max Activating Token Index: 196