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

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

Neuron 2929 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3511. Min Act: -0.0001

Data Index: 1046106 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3426. Min Act: -0.0000

Data Index: 817520 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2979. Min Act: -0.0001

Data Index: 298236 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2884. Min Act: -0.0001

Data Index: 513877 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2514. Min Act: -0.0000

Data Index: 3742 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2552. Min Act: -0.0000

Data Index: 760783 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2436. Min Act: -0.0000

Data Index: 1051563 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2170. Min Act: -0.0001

Data Index: 569430 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2241. Min Act: -0.0001

Data Index: 498145 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2184. Min Act: -0.0001

Data Index: 1002211 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2065. Min Act: -0.0001

Data Index: 964973 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2027. Min Act: -0.0001

Data Index: 289554 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2007. Min Act: -0.0001

Data Index: 84841 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.1978. Min Act: -0.0001

Data Index: 1163 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.1956. Min Act: -0.0001

Data Index: 1096200 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.1946. Min Act: -0.0001

Data Index: 342655 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2012. Min Act: -0.0000

Data Index: 817176 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.1911. Min Act: -0.0001

Data Index: 1069937 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.1848. Min Act: -0.0001

Data Index: 591165 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.1903. Min Act: -0.0000

Data Index: 777617 (C4 (Web Text))

Max Activating Token Index: 182