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

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

Neuron 453 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: 2.1243. Min Range: -2.1243

Max Act: 2.1243. Min Act: -0.0000

Data Index: 194030 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 2.1243. Min Range: -2.1243

Max Act: 1.5334. Min Act: -0.0000

Data Index: 840422 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 2.1243. Min Range: -2.1243

Max Act: 0.9890. Min Act: -0.0000

Data Index: 604686 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 2.1243. Min Range: -2.1243

Max Act: 0.9111. Min Act: -0.0000

Data Index: 993071 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 2.1243. Min Range: -2.1243

Max Act: 0.6144. Min Act: -0.0000

Data Index: 600264 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 2.1243. Min Range: -2.1243

Max Act: 0.7530. Min Act: -0.0000

Data Index: 1070612 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 2.1243. Min Range: -2.1243

Max Act: 0.7682. Min Act: -0.0000

Data Index: 88994 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 2.1243. Min Range: -2.1243

Max Act: 0.7915. Min Act: -0.0000

Data Index: 906933 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 2.1243. Min Range: -2.1243

Max Act: 0.6629. Min Act: -0.0000

Data Index: 92895 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 2.1243. Min Range: -2.1243

Max Act: 0.7078. Min Act: -0.0000

Data Index: 311458 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 2.1243. Min Range: -2.1243

Max Act: 0.6709. Min Act: -0.0000

Data Index: 1118256 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 2.1243. Min Range: -2.1243

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1040179 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 2.1243. Min Range: -2.1243

Max Act: 0.7902. Min Act: -0.0000

Data Index: 1143271 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 2.1243. Min Range: -2.1243

Max Act: 0.6943. Min Act: -0.0000

Data Index: 294721 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 2.1243. Min Range: -2.1243

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1325820 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 2.1243. Min Range: -2.1243

Max Act: 0.6749. Min Act: -0.0000

Data Index: 1223562 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 2.1243. Min Range: -2.1243

Max Act: 0.6446. Min Act: -0.0000

Data Index: 19842 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 2.1243. Min Range: -2.1243

Max Act: 0.5990. Min Act: -0.0000

Data Index: 466172 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 2.1243. Min Range: -2.1243

Max Act: 0.6841. Min Act: -0.0000

Data Index: 502106 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 2.1243. Min Range: -2.1243

Max Act: 0.6239. Min Act: -0.0000

Data Index: 430922 (C4 (Web Text))

Max Activating Token Index: 141