Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 729 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1301. Min Act: -0.0003

Data Index: 1287121 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1270. Min Act: -0.0003

Data Index: 1358543 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1114. Min Act: -0.0003

Data Index: 401058 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1100. Min Act: -0.0003

Data Index: 402134 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1142. Min Act: -0.0003

Data Index: 831946 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1162. Min Act: -0.0003

Data Index: 108144 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1114. Min Act: -0.0003

Data Index: 525875 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1135. Min Act: -0.0003

Data Index: 869126 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1067. Min Act: -0.0003

Data Index: 589743 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1101. Min Act: -0.0003

Data Index: 751864 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1082. Min Act: -0.0003

Data Index: 1120732 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1066. Min Act: -0.0003

Data Index: 847006 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1107. Min Act: -0.0003

Data Index: 704416 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1032. Min Act: -0.0003

Data Index: 851016 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0993. Min Act: -0.0003

Data Index: 330841 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1104. Min Act: -0.0003

Data Index: 316511 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1030. Min Act: -0.0003

Data Index: 11980 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1021. Min Act: -0.0003

Data Index: 762687 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1007. Min Act: -0.0003

Data Index: 545395 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1048. Min Act: -0.0003

Data Index: 1251985 (C4 (Web Text))

Max Activating Token Index: 741