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

Dataset: The Pile

Neuron 612 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5524. Min Act: -0.0000

Data Index: 464407 (The Pile)

Max Activating Token Index: 1013

Text #1

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1094184 (The Pile)

Max Activating Token Index: 597

Text #2

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.6399. Min Act: -0.0000

Data Index: 736356 (The Pile)

Max Activating Token Index: 572

Text #3

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.6706. Min Act: -0.0000

Data Index: 480152 (The Pile)

Max Activating Token Index: 980

Text #4

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5710. Min Act: -0.0000

Data Index: 1787384 (The Pile)

Max Activating Token Index: 473

Text #5

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5965. Min Act: -0.0000

Data Index: 660420 (The Pile)

Max Activating Token Index: 317

Text #6

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1399521 (The Pile)

Max Activating Token Index: 436

Text #7

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5679. Min Act: -0.0000

Data Index: 459303 (The Pile)

Max Activating Token Index: 848

Text #8

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5219. Min Act: -0.0000

Data Index: 1082601 (The Pile)

Max Activating Token Index: 623

Text #9

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.6575. Min Act: -0.0000

Data Index: 1405573 (The Pile)

Max Activating Token Index: 668

Text #10

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5361. Min Act: -0.0000

Data Index: 1833018 (The Pile)

Max Activating Token Index: 258

Text #11

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5305. Min Act: -0.0000

Data Index: 1242089 (The Pile)

Max Activating Token Index: 622

Text #12

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5831. Min Act: -0.0000

Data Index: 199614 (The Pile)

Max Activating Token Index: 862

Text #13

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5833. Min Act: -0.0000

Data Index: 168223 (The Pile)

Max Activating Token Index: 949

Text #14

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1154518 (The Pile)

Max Activating Token Index: 555

Text #15

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1162427 (The Pile)

Max Activating Token Index: 1017

Text #16

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.4629. Min Act: -0.0000

Data Index: 1593416 (The Pile)

Max Activating Token Index: 1019

Text #17

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5333. Min Act: -0.0000

Data Index: 1680653 (The Pile)

Max Activating Token Index: 786

Text #18

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5679. Min Act: -0.0000

Data Index: 487623 (The Pile)

Max Activating Token Index: 251

Text #19

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.4880. Min Act: -0.0000

Data Index: 205588 (The Pile)

Max Activating Token Index: 924