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

Dataset: The Pile

Neuron 1456 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: 0.8488. Min Range: -0.8488

Max Act: 0.7769. Min Act: -0.0000

Data Index: 757349 (The Pile)

Max Activating Token Index: 1020

Text #1

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.8488. Min Act: -0.0000

Data Index: 296385 (The Pile)

Max Activating Token Index: 646

Text #2

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.7026. Min Act: -0.0000

Data Index: 589539 (The Pile)

Max Activating Token Index: 395

Text #3

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.7566. Min Act: -0.0000

Data Index: 1067534 (The Pile)

Max Activating Token Index: 705

Text #4

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.7365. Min Act: -0.0000

Data Index: 1065599 (The Pile)

Max Activating Token Index: 976

Text #5

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6794. Min Act: -0.0000

Data Index: 1860806 (The Pile)

Max Activating Token Index: 345

Text #6

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6629. Min Act: 0.0000

Data Index: 6799 (The Pile)

Max Activating Token Index: 598

Text #7

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.7013. Min Act: -0.0000

Data Index: 225424 (The Pile)

Max Activating Token Index: 470

Text #8

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6877. Min Act: -0.0000

Data Index: 458416 (The Pile)

Max Activating Token Index: 644

Text #9

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6901. Min Act: -0.0000

Data Index: 1323954 (The Pile)

Max Activating Token Index: 751

Text #10

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6933. Min Act: -0.0000

Data Index: 819861 (The Pile)

Max Activating Token Index: 641

Text #11

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6737. Min Act: -0.0001

Data Index: 1690177 (The Pile)

Max Activating Token Index: 970

Text #12

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1751861 (The Pile)

Max Activating Token Index: 599

Text #13

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6505. Min Act: -0.0000

Data Index: 1036014 (The Pile)

Max Activating Token Index: 62

Text #14

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6480. Min Act: -0.0000

Data Index: 842550 (The Pile)

Max Activating Token Index: 921

Text #15

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6641. Min Act: -0.0000

Data Index: 1431904 (The Pile)

Max Activating Token Index: 595

Text #16

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1729930 (The Pile)

Max Activating Token Index: 45

Text #17

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1439322 (The Pile)

Max Activating Token Index: 747

Text #18

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6387. Min Act: -0.0000

Data Index: 268362 (The Pile)

Max Activating Token Index: 852

Text #19

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6367. Min Act: -0.0000

Data Index: 125676 (The Pile)

Max Activating Token Index: 978