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

Dataset: The Pile

Neuron 4058 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.5335. Min Act: -0.0001

Data Index: 1964079 (The Pile)

Max Activating Token Index: 933

Text #1

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.5237. Min Act: -0.0000

Data Index: 2695 (The Pile)

Max Activating Token Index: 447

Text #2

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4867. Min Act: -0.0000

Data Index: 575603 (The Pile)

Max Activating Token Index: 35

Text #3

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4779. Min Act: -0.0000

Data Index: 441674 (The Pile)

Max Activating Token Index: 63

Text #4

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4313. Min Act: -0.0000

Data Index: 332225 (The Pile)

Max Activating Token Index: 533

Text #5

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4512. Min Act: -0.0001

Data Index: 831170 (The Pile)

Max Activating Token Index: 172

Text #6

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4383. Min Act: -0.0000

Data Index: 427725 (The Pile)

Max Activating Token Index: 202

Text #7

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3929. Min Act: -0.0000

Data Index: 1041455 (The Pile)

Max Activating Token Index: 86

Text #8

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1664658 (The Pile)

Max Activating Token Index: 383

Text #9

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3945. Min Act: -0.0001

Data Index: 158262 (The Pile)

Max Activating Token Index: 354

Text #10

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3674. Min Act: -0.0000

Data Index: 1583534 (The Pile)

Max Activating Token Index: 73

Text #11

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3754. Min Act: -0.0001

Data Index: 1642696 (The Pile)

Max Activating Token Index: 142

Text #12

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3733. Min Act: -0.0000

Data Index: 405608 (The Pile)

Max Activating Token Index: 818

Text #13

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1263684 (The Pile)

Max Activating Token Index: 590

Text #14

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4022. Min Act: -0.0000

Data Index: 640020 (The Pile)

Max Activating Token Index: 125

Text #15

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3716. Min Act: -0.0000

Data Index: 1539418 (The Pile)

Max Activating Token Index: 180

Text #16

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3657. Min Act: -0.0001

Data Index: 805551 (The Pile)

Max Activating Token Index: 96

Text #17

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3497. Min Act: -0.0000

Data Index: 618581 (The Pile)

Max Activating Token Index: 300

Text #18

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3502. Min Act: -0.0000

Data Index: 1574214 (The Pile)

Max Activating Token Index: 297

Text #19

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3445. Min Act: -0.0001

Data Index: 1699444 (The Pile)

Max Activating Token Index: 1004