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

Dataset: The Pile

Neuron 5006 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.5680. Min Act: -0.0000

Data Index: 724992 (The Pile)

Max Activating Token Index: 187

Text #1

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4907. Min Act: -0.0000

Data Index: 1702733 (The Pile)

Max Activating Token Index: 76

Text #2

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1497807 (The Pile)

Max Activating Token Index: 951

Text #3

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4772. Min Act: -0.0000

Data Index: 1334856 (The Pile)

Max Activating Token Index: 553

Text #4

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4777. Min Act: -0.0000

Data Index: 1843533 (The Pile)

Max Activating Token Index: 167

Text #5

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4597. Min Act: -0.0000

Data Index: 14083 (The Pile)

Max Activating Token Index: 320

Text #6

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4712. Min Act: -0.0000

Data Index: 423273 (The Pile)

Max Activating Token Index: 928

Text #7

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4885. Min Act: -0.0000

Data Index: 490710 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4040. Min Act: -0.0000

Data Index: 1606475 (The Pile)

Max Activating Token Index: 726

Text #9

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4596. Min Act: -0.0000

Data Index: 1333171 (The Pile)

Max Activating Token Index: 362

Text #10

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1235427 (The Pile)

Max Activating Token Index: 73

Text #11

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1634583 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1963394 (The Pile)

Max Activating Token Index: 584

Text #13

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4396. Min Act: -0.0000

Data Index: 1931596 (The Pile)

Max Activating Token Index: 630

Text #14

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4138. Min Act: -0.0000

Data Index: 446022 (The Pile)

Max Activating Token Index: 565

Text #15

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4426. Min Act: -0.0000

Data Index: 1119570 (The Pile)

Max Activating Token Index: 921

Text #16

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4238. Min Act: -0.0000

Data Index: 168139 (The Pile)

Max Activating Token Index: 182

Text #17

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4379. Min Act: -0.0000

Data Index: 793292 (The Pile)

Max Activating Token Index: 436

Text #18

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4037. Min Act: -0.0000

Data Index: 971138 (The Pile)

Max Activating Token Index: 233

Text #19

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1664127 (The Pile)

Max Activating Token Index: 695