Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 160 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.7604. Min Act: -0.0001

Data Index: 300613 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.7642. Min Act: -0.0001

Data Index: 1178529 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.7367. Min Act: -0.0001

Data Index: 797206 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.6984. Min Act: -0.0001

Data Index: 128379 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.7051. Min Act: -0.0001

Data Index: 104069 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.6991. Min Act: -0.0001

Data Index: 1316201 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.7058. Min Act: -0.0001

Data Index: 244071 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.6812. Min Act: 0.0000

Data Index: 1079079 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.6786. Min Act: -0.0001

Data Index: 990557 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.6999. Min Act: -0.0001

Data Index: 162769 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.6729. Min Act: -0.0001

Data Index: 438819 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.6651. Min Act: -0.0001

Data Index: 430683 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.6608. Min Act: -0.0001

Data Index: 615414 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.6331. Min Act: -0.0001

Data Index: 391348 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.6270. Min Act: -0.0001

Data Index: 967074 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.6359. Min Act: -0.0001

Data Index: 1072816 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.6195. Min Act: -0.0001

Data Index: 398929 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.6334. Min Act: -0.0001

Data Index: 353972 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.6223. Min Act: -0.0001

Data Index: 354754 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.5679. Min Act: -0.0001

Data Index: 285101 (C4 (Web Text))

Max Activating Token Index: 78