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

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

Neuron 4660 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: 1.2085. Min Range: -1.2085

Max Act: 1.1601. Min Act: -0.0000

Data Index: 629232 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 1.2085. Min Range: -1.2085

Max Act: 1.2085. Min Act: -0.0000

Data Index: 191250 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 1.2085. Min Range: -1.2085

Max Act: 1.1027. Min Act: -0.0000

Data Index: 563962 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 1.2085. Min Range: -1.2085

Max Act: 1.0545. Min Act: -0.0000

Data Index: 135299 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9952. Min Act: -0.0000

Data Index: 606006 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 1.2085. Min Range: -1.2085

Max Act: 1.0701. Min Act: -0.0000

Data Index: 210961 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 1.2085. Min Range: -1.2085

Max Act: 1.1075. Min Act: -0.0000

Data Index: 1092183 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9852. Min Act: -0.0000

Data Index: 839174 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9674. Min Act: -0.0000

Data Index: 31833 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9102. Min Act: -0.0000

Data Index: 691906 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9319. Min Act: -0.0000

Data Index: 620448 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9493. Min Act: -0.0000

Data Index: 682134 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9659. Min Act: -0.0000

Data Index: 561932 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9091. Min Act: -0.0000

Data Index: 612749 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9315. Min Act: -0.0000

Data Index: 494424 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.8666. Min Act: -0.0000

Data Index: 504412 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9167. Min Act: -0.0000

Data Index: 657139 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.8539. Min Act: -0.0000

Data Index: 207042 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.8745. Min Act: -0.0000

Data Index: 158710 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.8506. Min Act: -0.0000

Data Index: 349603 (C4 (Web Text))

Max Activating Token Index: 326