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

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

Neuron 585 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.2024. Min Act: -0.0001

Data Index: 602218 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.2229. Min Act: -0.0001

Data Index: 805332 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.2424. Min Act: -0.0001

Data Index: 1179274 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.1705. Min Act: -0.0001

Data Index: 783962 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.1243. Min Act: -0.0001

Data Index: 457343 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.1472. Min Act: -0.0001

Data Index: 578836 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.0955. Min Act: -0.0001

Data Index: 365777 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.0519. Min Act: -0.0001

Data Index: 811278 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.1142. Min Act: -0.0001

Data Index: 816155 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 1.2424. Min Range: -1.2424

Max Act: 0.9864. Min Act: -0.0001

Data Index: 403345 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.0039. Min Act: -0.0001

Data Index: 37514 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.0496. Min Act: -0.0001

Data Index: 1046209 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 1.2424. Min Range: -1.2424

Max Act: 0.9780. Min Act: -0.0001

Data Index: 1351905 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.0051. Min Act: -0.0001

Data Index: 1007648 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 1.2424. Min Range: -1.2424

Max Act: 0.9700. Min Act: -0.0001

Data Index: 274817 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.0561. Min Act: -0.0001

Data Index: 134346 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.0195. Min Act: -0.0001

Data Index: 798066 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 1.2424. Min Range: -1.2424

Max Act: 0.9873. Min Act: -0.0001

Data Index: 365333 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 1.2424. Min Range: -1.2424

Max Act: 0.9841. Min Act: -0.0001

Data Index: 1136577 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.0067. Min Act: -0.0001

Data Index: 779893 (C4 (Web Text))

Max Activating Token Index: 778