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

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

Neuron 2866 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.2551. Min Act: -0.0000

Data Index: 1119570 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1131501 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.2228. Min Act: -0.0000

Data Index: 223617 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.2296. Min Act: -0.0000

Data Index: 584909 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.2032. Min Act: -0.0000

Data Index: 539488 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.2044. Min Act: -0.0000

Data Index: 125827 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1955. Min Act: -0.0000

Data Index: 572089 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1947. Min Act: -0.0000

Data Index: 953958 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1978. Min Act: -0.0000

Data Index: 355810 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1935. Min Act: -0.0000

Data Index: 36971 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1779. Min Act: -0.0000

Data Index: 1484160 (Python Code)

Max Activating Token Index: 304

Text #11

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1830. Min Act: -0.0000

Data Index: 637889 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1737. Min Act: -0.0000

Data Index: 629112 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1755. Min Act: -0.0000

Data Index: 433307 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1808. Min Act: -0.0000

Data Index: 472859 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1296293 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1732. Min Act: -0.0000

Data Index: 474375 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1772. Min Act: -0.0000

Data Index: 239377 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1720. Min Act: -0.0000

Data Index: 1528332 (Python Code)

Max Activating Token Index: 673

Text #19

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1658. Min Act: -0.0000

Data Index: 488756 (C4 (Web Text))

Max Activating Token Index: 148