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

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

Neuron 5371 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.3139. Min Act: -0.0001

Data Index: 794121 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2763. Min Act: -0.0001

Data Index: 618710 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2750. Min Act: -0.0000

Data Index: 198414 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2631. Min Act: -0.0001

Data Index: 820639 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2321. Min Act: -0.0000

Data Index: 1509345 (Python Code)

Max Activating Token Index: 844

Text #5

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2578. Min Act: -0.0001

Data Index: 200483 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2409. Min Act: -0.0001

Data Index: 543425 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2072. Min Act: -0.0000

Data Index: 883572 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2152. Min Act: -0.0000

Data Index: 1003567 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1216614 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2390. Min Act: -0.0001

Data Index: 118452 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2031. Min Act: -0.0001

Data Index: 1320173 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2297. Min Act: -0.0001

Data Index: 526403 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.1981. Min Act: -0.0001

Data Index: 504654 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2007. Min Act: -0.0001

Data Index: 943151 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.1971. Min Act: -0.0001

Data Index: 719574 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.1910. Min Act: -0.0000

Data Index: 54804 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.1832. Min Act: -0.0001

Data Index: 967586 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.1901. Min Act: -0.0000

Data Index: 628137 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2001. Min Act: -0.0000

Data Index: 106917 (C4 (Web Text))

Max Activating Token Index: 711