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

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

Neuron 965 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6898. Min Act: -0.0000

Data Index: 494643 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6943. Min Act: -0.0000

Data Index: 460379 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.7244. Min Act: -0.0000

Data Index: 1262800 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.7430. Min Act: -0.0000

Data Index: 980675 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6759. Min Act: -0.0000

Data Index: 779922 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6404. Min Act: -0.0000

Data Index: 887586 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6332. Min Act: -0.0000

Data Index: 564581 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6515. Min Act: -0.0000

Data Index: 265557 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.5947. Min Act: -0.0000

Data Index: 166437 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6480. Min Act: -0.0000

Data Index: 600855 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.5878. Min Act: -0.0000

Data Index: 115356 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.5871. Min Act: -0.0000

Data Index: 114281 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1010075 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.5409. Min Act: -0.0000

Data Index: 427490 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.5295. Min Act: -0.0000

Data Index: 1361350 (Python Code)

Max Activating Token Index: 815

Text #15

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.4891. Min Act: -0.0000

Data Index: 734735 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1309900 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1118502 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.4796. Min Act: -0.0000

Data Index: 856935 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.5128. Min Act: -0.0000

Data Index: 249590 (C4 (Web Text))

Max Activating Token Index: 490