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

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

Neuron 3563 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.8099. Min Act: -0.0000

Data Index: 1403833 (Python Code)

Max Activating Token Index: 536

Text #1

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.6635. Min Act: -0.0000

Data Index: 1560910 (Python Code)

Max Activating Token Index: 191

Text #2

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.5151. Min Act: -0.0000

Data Index: 1473574 (Python Code)

Max Activating Token Index: 541

Text #3

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.3956. Min Act: -0.0000

Data Index: 1539223 (Python Code)

Max Activating Token Index: 126

Text #4

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.2746. Min Act: -0.0000

Data Index: 1365586 (Python Code)

Max Activating Token Index: 69

Text #5

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.3526. Min Act: -0.0000

Data Index: 1652813 (Python Code)

Max Activating Token Index: 77

Text #6

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.3680. Min Act: -0.0000

Data Index: 1460235 (Python Code)

Max Activating Token Index: 894

Text #7

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.4025. Min Act: -0.0000

Data Index: 1532956 (Python Code)

Max Activating Token Index: 1019

Text #8

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.1867. Min Act: -0.0000

Data Index: 1631118 (Python Code)

Max Activating Token Index: 292

Text #9

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.2478. Min Act: -0.0001

Data Index: 1394700 (Python Code)

Max Activating Token Index: 272

Text #10

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.3728. Min Act: -0.0000

Data Index: 1595344 (Python Code)

Max Activating Token Index: 110

Text #11

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.2449. Min Act: -0.0000

Data Index: 1528321 (Python Code)

Max Activating Token Index: 670

Text #12

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.3510. Min Act: -0.0000

Data Index: 1544927 (Python Code)

Max Activating Token Index: 241

Text #13

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.3423. Min Act: -0.0000

Data Index: 1452803 (Python Code)

Max Activating Token Index: 877

Text #14

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.2659. Min Act: -0.0000

Data Index: 1651914 (Python Code)

Max Activating Token Index: 355

Text #15

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.1877. Min Act: -0.0000

Data Index: 1371224 (Python Code)

Max Activating Token Index: 119

Text #16

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.2718. Min Act: -0.0000

Data Index: 1576529 (Python Code)

Max Activating Token Index: 455

Text #17

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.2048. Min Act: -0.0000

Data Index: 1513452 (Python Code)

Max Activating Token Index: 897

Text #18

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.3112. Min Act: -0.0000

Data Index: 1599126 (Python Code)

Max Activating Token Index: 348

Text #19

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.2719. Min Act: -0.0000

Data Index: 1441072 (Python Code)

Max Activating Token Index: 148