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

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

Neuron 1496 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1053. Min Act: -0.0000

Data Index: 539984 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1509. Min Act: -0.0000

Data Index: 452786 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1209. Min Act: -0.0000

Data Index: 1611420 (Python Code)

Max Activating Token Index: 728

Text #3

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1210. Min Act: -0.0000

Data Index: 1187071 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1020. Min Act: -0.0000

Data Index: 1249583 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1257. Min Act: -0.0000

Data Index: 235091 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1255131 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1078. Min Act: -0.0000

Data Index: 748796 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1040. Min Act: -0.0000

Data Index: 7789 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0943. Min Act: -0.0000

Data Index: 1007875 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1072052 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0993. Min Act: -0.0000

Data Index: 137584 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0721. Min Act: -0.0000

Data Index: 117820 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0947. Min Act: -0.0000

Data Index: 214869 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0917. Min Act: -0.0000

Data Index: 518671 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1012. Min Act: -0.0000

Data Index: 1302322 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0917. Min Act: 0.0001

Data Index: 1448644 (Python Code)

Max Activating Token Index: 220

Text #17

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0928. Min Act: -0.0000

Data Index: 425489 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1001. Min Act: -0.0000

Data Index: 309497 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0961. Min Act: -0.0000

Data Index: 973743 (C4 (Web Text))

Max Activating Token Index: 38