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

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

Neuron 492 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1149. Min Act: -0.0000

Data Index: 1359153 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1023. Min Act: -0.0000

Data Index: 578321 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1243. Min Act: -0.0000

Data Index: 451139 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1356280 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1042. Min Act: -0.0001

Data Index: 991829 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1064. Min Act: -0.0000

Data Index: 1278904 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1094. Min Act: -0.0001

Data Index: 771042 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1076. Min Act: -0.0001

Data Index: 411196 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1088. Min Act: -0.0001

Data Index: 1028642 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1065. Min Act: -0.0000

Data Index: 19454 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1116. Min Act: -0.0000

Data Index: 237139 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1279321 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1026. Min Act: -0.0000

Data Index: 436042 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1084. Min Act: -0.0000

Data Index: 1160398 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0837. Min Act: -0.0000

Data Index: 426927 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0870. Min Act: -0.0000

Data Index: 519646 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1053. Min Act: -0.0000

Data Index: 133431 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0718. Min Act: -0.0000

Data Index: 212703 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0842. Min Act: -0.0000

Data Index: 50179 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0821. Min Act: -0.0000

Data Index: 486935 (C4 (Web Text))

Max Activating Token Index: 791