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

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

Neuron 5119 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: 3.4821. Min Range: -3.4821

Max Act: 3.4821. Min Act: -0.0000

Data Index: 278285 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 3.4821. Min Range: -3.4821

Max Act: 3.1374. Min Act: -0.0000

Data Index: 1156990 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 3.4821. Min Range: -3.4821

Max Act: 3.2705. Min Act: -0.0000

Data Index: 1091224 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 3.4821. Min Range: -3.4821

Max Act: 3.3592. Min Act: -0.0000

Data Index: 275664 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 3.4821. Min Range: -3.4821

Max Act: 3.1418. Min Act: -0.0000

Data Index: 144552 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 3.4821. Min Range: -3.4821

Max Act: 2.9669. Min Act: -0.0000

Data Index: 148578 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 3.4821. Min Range: -3.4821

Max Act: 2.9989. Min Act: -0.0000

Data Index: 612862 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 3.4821. Min Range: -3.4821

Max Act: 2.9345. Min Act: -0.0000

Data Index: 918967 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 3.4821. Min Range: -3.4821

Max Act: 2.9193. Min Act: -0.0000

Data Index: 551448 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 3.4821. Min Range: -3.4821

Max Act: 2.6570. Min Act: -0.0000

Data Index: 1188448 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 3.4821. Min Range: -3.4821

Max Act: 2.6266. Min Act: -0.0000

Data Index: 83241 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 3.4821. Min Range: -3.4821

Max Act: 2.7637. Min Act: -0.0000

Data Index: 894594 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 3.4821. Min Range: -3.4821

Max Act: 2.6119. Min Act: -0.0000

Data Index: 159001 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 3.4821. Min Range: -3.4821

Max Act: 2.7103. Min Act: -0.0000

Data Index: 837194 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 3.4821. Min Range: -3.4821

Max Act: 2.5499. Min Act: -0.0000

Data Index: 990953 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 3.4821. Min Range: -3.4821

Max Act: 2.6855. Min Act: -0.0000

Data Index: 641823 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 3.4821. Min Range: -3.4821

Max Act: 2.6422. Min Act: -0.0000

Data Index: 781186 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 3.4821. Min Range: -3.4821

Max Act: 2.4574. Min Act: -0.0000

Data Index: 6781 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 3.4821. Min Range: -3.4821

Max Act: 2.5754. Min Act: -0.0000

Data Index: 285324 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 3.4821. Min Range: -3.4821

Max Act: 2.4938. Min Act: -0.0000

Data Index: 987189 (C4 (Web Text))

Max Activating Token Index: 548