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

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

Neuron 5363 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1961. Min Range: -1.1961

Max Act: 1.1961. Min Act: -0.0000

Data Index: 376175 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 1.1961. Min Range: -1.1961

Max Act: 1.1219. Min Act: -0.0000

Data Index: 811679 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 1.1961. Min Range: -1.1961

Max Act: 1.0770. Min Act: -0.0000

Data Index: 21125 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 1.1961. Min Range: -1.1961

Max Act: 1.0056. Min Act: -0.0000

Data Index: 1222375 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 1.1961. Min Range: -1.1961

Max Act: 1.0114. Min Act: -0.0000

Data Index: 1231113 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.9818. Min Act: -0.0000

Data Index: 1202076 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.9406. Min Act: -0.0000

Data Index: 246126 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 1.1961. Min Range: -1.1961

Max Act: 1.0751. Min Act: -0.0000

Data Index: 1107673 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.9052. Min Act: -0.0000

Data Index: 207747 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.9778. Min Act: -0.0000

Data Index: 1205159 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.9329. Min Act: -0.0000

Data Index: 1322147 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1167081 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1224953 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.9195. Min Act: -0.0000

Data Index: 391990 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8430. Min Act: -0.0000

Data Index: 991866 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8322. Min Act: -0.0000

Data Index: 274325 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1281973 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8408. Min Act: -0.0000

Data Index: 19212 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8054. Min Act: -0.0000

Data Index: 434805 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.9386. Min Act: -0.0000

Data Index: 903672 (C4 (Web Text))

Max Activating Token Index: 882