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

Dataset: The Pile

Neuron 4857 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.8577. Min Act: -0.0000

Data Index: 1496752 (The Pile)

Max Activating Token Index: 91

Text #1

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.5300. Min Act: -0.0000

Data Index: 1839320 (The Pile)

Max Activating Token Index: 1000

Text #2

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.7620. Min Act: -0.0000

Data Index: 1674822 (The Pile)

Max Activating Token Index: 895

Text #3

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.5155. Min Act: -0.0000

Data Index: 1701082 (The Pile)

Max Activating Token Index: 239

Text #4

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.4984. Min Act: -0.0000

Data Index: 901621 (The Pile)

Max Activating Token Index: 736

Text #5

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.3906. Min Act: -0.0000

Data Index: 64412 (The Pile)

Max Activating Token Index: 233

Text #6

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.4017. Min Act: -0.0000

Data Index: 460030 (The Pile)

Max Activating Token Index: 74

Text #7

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.4703. Min Act: -0.0000

Data Index: 1801333 (The Pile)

Max Activating Token Index: 296

Text #8

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.3827. Min Act: -0.0000

Data Index: 1245506 (The Pile)

Max Activating Token Index: 256

Text #9

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.2963. Min Act: -0.0000

Data Index: 819564 (The Pile)

Max Activating Token Index: 1011

Text #10

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.3961. Min Act: -0.0000

Data Index: 195929 (The Pile)

Max Activating Token Index: 894

Text #11

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.2601. Min Act: -0.0000

Data Index: 123676 (The Pile)

Max Activating Token Index: 375

Text #12

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.2521. Min Act: -0.0000

Data Index: 759688 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.2426. Min Act: -0.0000

Data Index: 1523411 (The Pile)

Max Activating Token Index: 285

Text #14

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.2455. Min Act: -0.0000

Data Index: 1335331 (The Pile)

Max Activating Token Index: 135

Text #15

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.1715. Min Act: -0.0000

Data Index: 636488 (The Pile)

Max Activating Token Index: 770

Text #16

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.2514. Min Act: -0.0000

Data Index: 1538082 (The Pile)

Max Activating Token Index: 692

Text #17

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.2100. Min Act: -0.0000

Data Index: 1092508 (The Pile)

Max Activating Token Index: 224

Text #18

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.2439. Min Act: -0.0000

Data Index: 364302 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.2445. Min Act: -0.0000

Data Index: 34483 (The Pile)

Max Activating Token Index: 691