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

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

Neuron 2790 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.2175. Min Act: -0.0000

Data Index: 1147186 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.2054. Min Act: -0.0000

Data Index: 193214 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1925. Min Act: -0.0000

Data Index: 1209867 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1753. Min Act: -0.0000

Data Index: 704369 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1629. Min Act: -0.0000

Data Index: 327078 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1588. Min Act: -0.0000

Data Index: 335923 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1640. Min Act: -0.0000

Data Index: 194839 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1699. Min Act: -0.0000

Data Index: 898374 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1537. Min Act: -0.0000

Data Index: 760657 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1626. Min Act: -0.0000

Data Index: 227271 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1576. Min Act: -0.0000

Data Index: 942738 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1459. Min Act: -0.0000

Data Index: 1215196 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1481. Min Act: -0.0000

Data Index: 973000 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1548. Min Act: -0.0000

Data Index: 578187 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1397. Min Act: -0.0000

Data Index: 975245 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1321. Min Act: -0.0000

Data Index: 793205 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1410. Min Act: -0.0000

Data Index: 62982 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1512. Min Act: -0.0000

Data Index: 16946 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1240. Min Act: -0.0000

Data Index: 1026895 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1515. Min Act: -0.0000

Data Index: 1020483 (C4 (Web Text))

Max Activating Token Index: 81