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

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

Neuron 4114 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8088. Min Range: -2.8088

Max Act: 2.8088. Min Act: -0.0000

Data Index: 1323263 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 2.8088. Min Range: -2.8088

Max Act: 2.8031. Min Act: -0.0000

Data Index: 1021564 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 2.8088. Min Range: -2.8088

Max Act: 2.7130. Min Act: -0.0000

Data Index: 1138399 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 2.8088. Min Range: -2.8088

Max Act: 2.5229. Min Act: -0.0000

Data Index: 84639 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 2.8088. Min Range: -2.8088

Max Act: 2.5747. Min Act: -0.0000

Data Index: 1064154 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 2.8088. Min Range: -2.8088

Max Act: 2.5716. Min Act: -0.0000

Data Index: 1346547 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 2.8088. Min Range: -2.8088

Max Act: 2.6400. Min Act: -0.0000

Data Index: 486467 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 2.8088. Min Range: -2.8088

Max Act: 2.4902. Min Act: -0.0000

Data Index: 544445 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 2.8088. Min Range: -2.8088

Max Act: 2.5624. Min Act: -0.0000

Data Index: 329357 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 2.8088. Min Range: -2.8088

Max Act: 2.4931. Min Act: -0.0000

Data Index: 671827 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 2.8088. Min Range: -2.8088

Max Act: 2.4546. Min Act: -0.0000

Data Index: 52151 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 2.8088. Min Range: -2.8088

Max Act: 2.2715. Min Act: -0.0000

Data Index: 1062869 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 2.8088. Min Range: -2.8088

Max Act: 2.4268. Min Act: -0.0000

Data Index: 238383 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 2.8088. Min Range: -2.8088

Max Act: 2.4189. Min Act: -0.0000

Data Index: 358912 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 2.8088. Min Range: -2.8088

Max Act: 2.3566. Min Act: -0.0000

Data Index: 1405445 (Python Code)

Max Activating Token Index: 415

Text #15

Max Range: 2.8088. Min Range: -2.8088

Max Act: 2.3008. Min Act: -0.0000

Data Index: 548678 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 2.8088. Min Range: -2.8088

Max Act: 2.3061. Min Act: -0.0000

Data Index: 1636085 (Python Code)

Max Activating Token Index: 755

Text #17

Max Range: 2.8088. Min Range: -2.8088

Max Act: 2.4281. Min Act: -0.0000

Data Index: 1076003 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 2.8088. Min Range: -2.8088

Max Act: 2.3307. Min Act: -0.0000

Data Index: 1050929 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 2.8088. Min Range: -2.8088

Max Act: 2.2955. Min Act: -0.0000

Data Index: 452363 (C4 (Web Text))

Max Activating Token Index: 853