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

Dataset: The Pile

Neuron 2748 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.9985. Min Act: -0.0000

Data Index: 730897 (The Pile)

Max Activating Token Index: 214

Text #1

Max Range: 1.0175. Min Range: -1.0175

Max Act: 1.0175. Min Act: -0.0000

Data Index: 688471 (The Pile)

Max Activating Token Index: 930

Text #2

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.9226. Min Act: -0.0000

Data Index: 403295 (The Pile)

Max Activating Token Index: 263

Text #3

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.8431. Min Act: -0.0000

Data Index: 916937 (The Pile)

Max Activating Token Index: 693

Text #4

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.7834. Min Act: -0.0000

Data Index: 1358429 (The Pile)

Max Activating Token Index: 457

Text #5

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.8052. Min Act: -0.0000

Data Index: 120397 (The Pile)

Max Activating Token Index: 639

Text #6

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.7978. Min Act: -0.0000

Data Index: 219822 (The Pile)

Max Activating Token Index: 136

Text #7

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.7924. Min Act: -0.0000

Data Index: 1869296 (The Pile)

Max Activating Token Index: 396

Text #8

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1635565 (The Pile)

Max Activating Token Index: 1020

Text #9

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.7550. Min Act: -0.0000

Data Index: 171320 (The Pile)

Max Activating Token Index: 377

Text #10

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.7797. Min Act: -0.0000

Data Index: 682593 (The Pile)

Max Activating Token Index: 499

Text #11

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.7333. Min Act: -0.0000

Data Index: 1957332 (The Pile)

Max Activating Token Index: 541

Text #12

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.8060. Min Act: -0.0000

Data Index: 1067348 (The Pile)

Max Activating Token Index: 113

Text #13

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.7450. Min Act: -0.0000

Data Index: 1255757 (The Pile)

Max Activating Token Index: 394

Text #14

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.7647. Min Act: -0.0000

Data Index: 1017501 (The Pile)

Max Activating Token Index: 675

Text #15

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.7210. Min Act: -0.0000

Data Index: 902400 (The Pile)

Max Activating Token Index: 1007

Text #16

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.7456. Min Act: -0.0000

Data Index: 1247146 (The Pile)

Max Activating Token Index: 627

Text #17

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.7651. Min Act: -0.0000

Data Index: 153035 (The Pile)

Max Activating Token Index: 722

Text #18

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.7567. Min Act: -0.0000

Data Index: 396219 (The Pile)

Max Activating Token Index: 612

Text #19

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.7127. Min Act: -0.0000

Data Index: 303463 (The Pile)

Max Activating Token Index: 226