Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3994 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7567. Min Act: -0.0000

Data Index: 714151 (The Pile)

Max Activating Token Index: 347

Text #1

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7688. Min Act: -0.0000

Data Index: 46351 (The Pile)

Max Activating Token Index: 543

Text #2

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1284437 (The Pile)

Max Activating Token Index: 203

Text #3

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7794. Min Act: -0.0000

Data Index: 695957 (The Pile)

Max Activating Token Index: 72

Text #4

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.8659. Min Act: -0.0000

Data Index: 1198272 (The Pile)

Max Activating Token Index: 227

Text #5

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7531. Min Act: -0.0000

Data Index: 744154 (The Pile)

Max Activating Token Index: 865

Text #6

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.8158. Min Act: -0.0000

Data Index: 171545 (The Pile)

Max Activating Token Index: 895

Text #7

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7536. Min Act: -0.0000

Data Index: 1537068 (The Pile)

Max Activating Token Index: 744

Text #8

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7873. Min Act: -0.0000

Data Index: 814379 (The Pile)

Max Activating Token Index: 98

Text #9

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7680. Min Act: -0.0000

Data Index: 495511 (The Pile)

Max Activating Token Index: 257

Text #10

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7403. Min Act: -0.0000

Data Index: 1296225 (The Pile)

Max Activating Token Index: 519

Text #11

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7012. Min Act: -0.0000

Data Index: 399501 (The Pile)

Max Activating Token Index: 93

Text #12

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.6889. Min Act: -0.0000

Data Index: 463699 (The Pile)

Max Activating Token Index: 92

Text #13

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1368937 (The Pile)

Max Activating Token Index: 183

Text #14

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.6939. Min Act: -0.0000

Data Index: 1050588 (The Pile)

Max Activating Token Index: 831

Text #15

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1877624 (The Pile)

Max Activating Token Index: 419

Text #16

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7086. Min Act: -0.0000

Data Index: 552125 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.7037. Min Act: -0.0000

Data Index: 1185763 (The Pile)

Max Activating Token Index: 196

Text #18

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.6962. Min Act: -0.0000

Data Index: 591510 (The Pile)

Max Activating Token Index: 56

Text #19

Max Range: 0.8659. Min Range: -0.8659

Max Act: 0.6229. Min Act: -0.0000

Data Index: 1074622 (The Pile)

Max Activating Token Index: 207