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

Dataset: The Pile

Neuron 4520 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: 0.5547. Min Range: -0.5547

Max Act: 0.5547. Min Act: -0.0000

Data Index: 270646 (The Pile)

Max Activating Token Index: 454

Text #1

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4224. Min Act: -0.0000

Data Index: 507403 (The Pile)

Max Activating Token Index: 962

Text #2

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4266. Min Act: -0.0000

Data Index: 348492 (The Pile)

Max Activating Token Index: 942

Text #3

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4338. Min Act: -0.0000

Data Index: 272985 (The Pile)

Max Activating Token Index: 454

Text #4

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4187. Min Act: -0.0000

Data Index: 955074 (The Pile)

Max Activating Token Index: 865

Text #5

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4385. Min Act: -0.0000

Data Index: 1219624 (The Pile)

Max Activating Token Index: 324

Text #6

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4160. Min Act: -0.0000

Data Index: 1533014 (The Pile)

Max Activating Token Index: 430

Text #7

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4416. Min Act: -0.0000

Data Index: 1551127 (The Pile)

Max Activating Token Index: 334

Text #8

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4031. Min Act: -0.0000

Data Index: 161102 (The Pile)

Max Activating Token Index: 615

Text #9

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4213. Min Act: -0.0000

Data Index: 257644 (The Pile)

Max Activating Token Index: 325

Text #10

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4100. Min Act: -0.0000

Data Index: 954901 (The Pile)

Max Activating Token Index: 449

Text #11

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3804. Min Act: -0.0000

Data Index: 69835 (The Pile)

Max Activating Token Index: 372

Text #12

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3789. Min Act: -0.0000

Data Index: 113717 (The Pile)

Max Activating Token Index: 267

Text #13

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3659. Min Act: -0.0000

Data Index: 1645391 (The Pile)

Max Activating Token Index: 178

Text #14

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4379. Min Act: -0.0000

Data Index: 8820 (The Pile)

Max Activating Token Index: 86

Text #15

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1584331 (The Pile)

Max Activating Token Index: 285

Text #16

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3594. Min Act: -0.0000

Data Index: 981425 (The Pile)

Max Activating Token Index: 73

Text #17

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3367. Min Act: -0.0000

Data Index: 1882498 (The Pile)

Max Activating Token Index: 928

Text #18

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1932912 (The Pile)

Max Activating Token Index: 567

Text #19

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3806. Min Act: -0.0000

Data Index: 96843 (The Pile)

Max Activating Token Index: 960