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

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

Neuron 4008 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6528. Min Range: -2.6528

Max Act: 2.6528. Min Act: -0.0000

Data Index: 181866 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 2.6528. Min Range: -2.6528

Max Act: 2.4708. Min Act: -0.0000

Data Index: 1160945 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 2.6528. Min Range: -2.6528

Max Act: 2.3820. Min Act: -0.0000

Data Index: 81129 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 2.6528. Min Range: -2.6528

Max Act: 2.2477. Min Act: -0.0000

Data Index: 134628 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 2.6528. Min Range: -2.6528

Max Act: 2.2165. Min Act: -0.0000

Data Index: 390039 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 2.6528. Min Range: -2.6528

Max Act: 2.2939. Min Act: -0.0000

Data Index: 540602 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 2.6528. Min Range: -2.6528

Max Act: 2.2682. Min Act: -0.0000

Data Index: 628483 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 2.6528. Min Range: -2.6528

Max Act: 2.2615. Min Act: -0.0000

Data Index: 825213 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 2.6528. Min Range: -2.6528

Max Act: 2.2462. Min Act: -0.0000

Data Index: 370665 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 2.6528. Min Range: -2.6528

Max Act: 2.1235. Min Act: -0.0000

Data Index: 786719 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 2.6528. Min Range: -2.6528

Max Act: 2.3592. Min Act: -0.0000

Data Index: 257365 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 2.6528. Min Range: -2.6528

Max Act: 2.3686. Min Act: -0.0000

Data Index: 668773 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 2.6528. Min Range: -2.6528

Max Act: 2.2230. Min Act: -0.0000

Data Index: 1007626 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 2.6528. Min Range: -2.6528

Max Act: 2.2432. Min Act: -0.0000

Data Index: 376973 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 2.6528. Min Range: -2.6528

Max Act: 2.0899. Min Act: -0.0000

Data Index: 1254685 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 2.6528. Min Range: -2.6528

Max Act: 2.2069. Min Act: -0.0000

Data Index: 913259 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 2.6528. Min Range: -2.6528

Max Act: 2.3210. Min Act: -0.0000

Data Index: 115861 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 2.6528. Min Range: -2.6528

Max Act: 2.3121. Min Act: -0.0000

Data Index: 825902 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 2.6528. Min Range: -2.6528

Max Act: 2.1961. Min Act: -0.0000

Data Index: 791699 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 2.6528. Min Range: -2.6528

Max Act: 2.2024. Min Act: -0.0000

Data Index: 681807 (C4 (Web Text))

Max Activating Token Index: 696