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

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

Neuron 4879 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: 0.4671. Min Range: -0.4671

Max Act: 0.4671. Min Act: 0.0000

Data Index: 103473 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.4151. Min Act: 0.0000

Data Index: 7296 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3934. Min Act: 0.0000

Data Index: 965420 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3924. Min Act: 0.0000

Data Index: 726892 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3900. Min Act: -0.0000

Data Index: 413751 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3937. Min Act: 0.0000

Data Index: 1304530 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3376. Min Act: -0.0000

Data Index: 787365 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3719. Min Act: -0.0000

Data Index: 946968 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3712. Min Act: 0.0000

Data Index: 201546 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3452. Min Act: 0.0000

Data Index: 755170 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3409. Min Act: -0.0000

Data Index: 935573 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3444. Min Act: 0.0000

Data Index: 815001 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3328. Min Act: 0.0000

Data Index: 140578 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3271. Min Act: -0.0000

Data Index: 1192771 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3274. Min Act: -0.0000

Data Index: 1257777 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3287. Min Act: -0.0000

Data Index: 716458 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3284. Min Act: -0.0000

Data Index: 147268 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3300. Min Act: 0.0000

Data Index: 21055 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3262. Min Act: 0.0000

Data Index: 1235271 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3342. Min Act: 0.0000

Data Index: 967983 (C4 (Web Text))

Max Activating Token Index: 318