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

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

Neuron 1432 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: 3.1882. Min Range: -3.1882

Max Act: 3.1882. Min Act: -0.0001

Data Index: 695406 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 3.1882. Min Range: -3.1882

Max Act: 2.8956. Min Act: -0.0000

Data Index: 58187 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 3.1882. Min Range: -3.1882

Max Act: 2.9958. Min Act: -0.0000

Data Index: 246892 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 3.1882. Min Range: -3.1882

Max Act: 2.7658. Min Act: -0.0000

Data Index: 550065 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 3.1882. Min Range: -3.1882

Max Act: 2.6448. Min Act: -0.0000

Data Index: 1198424 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 3.1882. Min Range: -3.1882

Max Act: 2.6324. Min Act: -0.0000

Data Index: 639755 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 3.1882. Min Range: -3.1882

Max Act: 2.7008. Min Act: -0.0000

Data Index: 895683 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 3.1882. Min Range: -3.1882

Max Act: 2.4706. Min Act: -0.0000

Data Index: 264923 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 3.1882. Min Range: -3.1882

Max Act: 2.2006. Min Act: -0.0000

Data Index: 1088616 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 3.1882. Min Range: -3.1882

Max Act: 2.5111. Min Act: -0.0001

Data Index: 1271964 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 3.1882. Min Range: -3.1882

Max Act: 2.6225. Min Act: -0.0000

Data Index: 781572 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 3.1882. Min Range: -3.1882

Max Act: 2.4735. Min Act: -0.0000

Data Index: 680992 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 3.1882. Min Range: -3.1882

Max Act: 2.2134. Min Act: -0.0000

Data Index: 123051 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 3.1882. Min Range: -3.1882

Max Act: 2.3146. Min Act: -0.0000

Data Index: 1094646 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 3.1882. Min Range: -3.1882

Max Act: 2.2975. Min Act: -0.0000

Data Index: 848280 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 3.1882. Min Range: -3.1882

Max Act: 2.3053. Min Act: -0.0000

Data Index: 1111609 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 3.1882. Min Range: -3.1882

Max Act: 2.3952. Min Act: -0.0000

Data Index: 397929 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 3.1882. Min Range: -3.1882

Max Act: 2.3606. Min Act: -0.0000

Data Index: 362212 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 3.1882. Min Range: -3.1882

Max Act: 2.4701. Min Act: -0.0000

Data Index: 239469 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 3.1882. Min Range: -3.1882

Max Act: 2.3510. Min Act: -0.0000

Data Index: 310246 (C4 (Web Text))

Max Activating Token Index: 263