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

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

Neuron 4013 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1539. Min Range: -1.1539

Max Act: 1.1539. Min Act: -0.0000

Data Index: 379313 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 1.1539. Min Range: -1.1539

Max Act: 1.1476. Min Act: -0.0000

Data Index: 479621 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 1.1539. Min Range: -1.1539

Max Act: 1.1359. Min Act: -0.0000

Data Index: 14082 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 1.1539. Min Range: -1.1539

Max Act: 1.1263. Min Act: -0.0000

Data Index: 172622 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 1.1539. Min Range: -1.1539

Max Act: 1.0182. Min Act: -0.0000

Data Index: 59458 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.8901. Min Act: -0.0000

Data Index: 631374 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.8381. Min Act: -0.0000

Data Index: 992115 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.8576. Min Act: -0.0000

Data Index: 212983 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1044143 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.7555. Min Act: -0.0000

Data Index: 1108943 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.8093. Min Act: -0.0000

Data Index: 1350774 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.7266. Min Act: -0.0000

Data Index: 464162 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.7919. Min Act: -0.0000

Data Index: 122741 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.7351. Min Act: -0.0000

Data Index: 25742 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.7584. Min Act: -0.0000

Data Index: 963945 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.7509. Min Act: -0.0000

Data Index: 340693 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1134420 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.6883. Min Act: -0.0000

Data Index: 160222 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.7344. Min Act: -0.0000

Data Index: 345288 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 1.1539. Min Range: -1.1539

Max Act: 0.7338. Min Act: -0.0000

Data Index: 798002 (C4 (Web Text))

Max Activating Token Index: 465