Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 915 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.3720. Min Act: -0.0000

Data Index: 1179581 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.2942. Min Act: -0.0000

Data Index: 333540 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.2518. Min Act: -0.0000

Data Index: 676082 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.2434. Min Act: -0.0000

Data Index: 690897 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.1416. Min Act: -0.0000

Data Index: 1193830 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.1257. Min Act: -0.0000

Data Index: 921472 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.1220. Min Act: -0.0000

Data Index: 834971 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.1155. Min Act: 0.0000

Data Index: 1122918 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1321540 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0885. Min Act: -0.0000

Data Index: 675380 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0801. Min Act: -0.0000

Data Index: 342647 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.1314. Min Act: -0.0000

Data Index: 839387 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0060. Min Act: -0.0000

Data Index: 1149538 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0602. Min Act: -0.0000

Data Index: 1259327 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.9856. Min Act: 0.0000

Data Index: 204539 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0555. Min Act: -0.0000

Data Index: 8039 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0499. Min Act: 0.0000

Data Index: 797037 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0037. Min Act: -0.0000

Data Index: 844181 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0338. Min Act: -0.0000

Data Index: 1290828 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0878. Min Act: -0.0000

Data Index: 687332 (C4 (Web Text))

Max Activating Token Index: 654