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

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

Neuron 445 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: 2.0666. Min Range: -2.0666

Max Act: 2.0655. Min Act: -0.0000

Data Index: 163661 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 2.0666. Min Range: -2.0666

Max Act: 2.0666. Min Act: -0.0000

Data Index: 820726 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 2.0666. Min Range: -2.0666

Max Act: 1.6250. Min Act: -0.0000

Data Index: 521383 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 2.0666. Min Range: -2.0666

Max Act: 1.7137. Min Act: -0.0000

Data Index: 549218 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 2.0666. Min Range: -2.0666

Max Act: 1.3384. Min Act: -0.0000

Data Index: 648543 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 2.0666. Min Range: -2.0666

Max Act: 1.3247. Min Act: -0.0000

Data Index: 1025476 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 2.0666. Min Range: -2.0666

Max Act: 1.3217. Min Act: -0.0000

Data Index: 599279 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 2.0666. Min Range: -2.0666

Max Act: 1.0174. Min Act: -0.0000

Data Index: 785288 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 2.0666. Min Range: -2.0666

Max Act: 1.2162. Min Act: -0.0000

Data Index: 886756 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 2.0666. Min Range: -2.0666

Max Act: 1.3634. Min Act: -0.0000

Data Index: 202 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 2.0666. Min Range: -2.0666

Max Act: 1.1985. Min Act: -0.0000

Data Index: 796823 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 2.0666. Min Range: -2.0666

Max Act: 1.1604. Min Act: -0.0000

Data Index: 791317 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 2.0666. Min Range: -2.0666

Max Act: 1.1528. Min Act: -0.0000

Data Index: 103920 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 2.0666. Min Range: -2.0666

Max Act: 1.2163. Min Act: -0.0000

Data Index: 1013900 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 2.0666. Min Range: -2.0666

Max Act: 1.2064. Min Act: -0.0000

Data Index: 406810 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 2.0666. Min Range: -2.0666

Max Act: 1.1972. Min Act: -0.0000

Data Index: 228089 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 2.0666. Min Range: -2.0666

Max Act: 1.2043. Min Act: -0.0000

Data Index: 419452 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 2.0666. Min Range: -2.0666

Max Act: 1.3453. Min Act: -0.0000

Data Index: 356045 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 2.0666. Min Range: -2.0666

Max Act: 1.2627. Min Act: -0.0000

Data Index: 1254904 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 2.0666. Min Range: -2.0666

Max Act: 1.1777. Min Act: -0.0000

Data Index: 781547 (C4 (Web Text))

Max Activating Token Index: 808