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

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

Neuron 1425 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.3703. Min Act: -0.0000

Data Index: 986884 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.3367. Min Act: -0.0000

Data Index: 226887 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1605457 (Python Code)

Max Activating Token Index: 974

Text #3

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2440. Min Act: -0.0000

Data Index: 1143034 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2439. Min Act: -0.0000

Data Index: 869080 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2332. Min Act: -0.0000

Data Index: 536201 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2102. Min Act: -0.0000

Data Index: 872077 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2111. Min Act: -0.0000

Data Index: 575019 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2109. Min Act: -0.0000

Data Index: 1138414 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1316009 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.1943. Min Act: -0.0000

Data Index: 980001 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.1883. Min Act: -0.0000

Data Index: 1351029 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.1898. Min Act: -0.0000

Data Index: 804907 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.1964. Min Act: -0.0000

Data Index: 454102 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2209. Min Act: -0.0000

Data Index: 917750 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.1768. Min Act: -0.0000

Data Index: 393189 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.1798. Min Act: -0.0000

Data Index: 778638 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.1908. Min Act: 0.0000

Data Index: 811399 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.1862. Min Act: -0.0000

Data Index: 954659 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1173328 (C4 (Web Text))

Max Activating Token Index: 247