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

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

Neuron 445 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3415. Min Range: -2.3415

Max Act: 2.3415. Min Act: -0.0000

Data Index: 24253 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 2.3415. Min Range: -2.3415

Max Act: 2.1050. Min Act: -0.0000

Data Index: 587170 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 2.3415. Min Range: -2.3415

Max Act: 1.9202. Min Act: -0.0000

Data Index: 34504 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 2.3415. Min Range: -2.3415

Max Act: 2.0069. Min Act: -0.0000

Data Index: 937713 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 2.3415. Min Range: -2.3415

Max Act: 1.9484. Min Act: -0.0000

Data Index: 113306 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 2.3415. Min Range: -2.3415

Max Act: 1.7883. Min Act: -0.0000

Data Index: 375368 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 2.3415. Min Range: -2.3415

Max Act: 1.8499. Min Act: -0.0000

Data Index: 514120 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 2.3415. Min Range: -2.3415

Max Act: 1.8467. Min Act: -0.0000

Data Index: 1268754 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 2.3415. Min Range: -2.3415

Max Act: 1.7387. Min Act: -0.0000

Data Index: 1291349 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 2.3415. Min Range: -2.3415

Max Act: 1.7140. Min Act: -0.0000

Data Index: 1162304 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 2.3415. Min Range: -2.3415

Max Act: 1.8177. Min Act: -0.0000

Data Index: 647917 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 2.3415. Min Range: -2.3415

Max Act: 1.6014. Min Act: -0.0000

Data Index: 450189 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 2.3415. Min Range: -2.3415

Max Act: 1.7838. Min Act: -0.0000

Data Index: 700609 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 2.3415. Min Range: -2.3415

Max Act: 1.7806. Min Act: -0.0000

Data Index: 230834 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 2.3415. Min Range: -2.3415

Max Act: 1.8720. Min Act: -0.0000

Data Index: 323735 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 2.3415. Min Range: -2.3415

Max Act: 1.6649. Min Act: -0.0000

Data Index: 266672 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 2.3415. Min Range: -2.3415

Max Act: 1.7589. Min Act: -0.0000

Data Index: 40349 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 2.3415. Min Range: -2.3415

Max Act: 1.7545. Min Act: -0.0000

Data Index: 609851 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 2.3415. Min Range: -2.3415

Max Act: 1.7497. Min Act: -0.0000

Data Index: 783959 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 2.3415. Min Range: -2.3415

Max Act: 1.6581. Min Act: -0.0000

Data Index: 971547 (C4 (Web Text))

Max Activating Token Index: 269