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

Dataset: The Pile

Neuron 3516 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: 0.6745. Min Range: -0.6745

Max Act: 0.6745. Min Act: -0.0000

Data Index: 305262 (The Pile)

Max Activating Token Index: 401

Text #1

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6147. Min Act: -0.0000

Data Index: 52014 (The Pile)

Max Activating Token Index: 692

Text #2

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5974. Min Act: -0.0000

Data Index: 1114211 (The Pile)

Max Activating Token Index: 618

Text #3

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6146. Min Act: -0.0000

Data Index: 1566203 (The Pile)

Max Activating Token Index: 305

Text #4

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1053211 (The Pile)

Max Activating Token Index: 663

Text #5

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5987. Min Act: -0.0000

Data Index: 55308 (The Pile)

Max Activating Token Index: 310

Text #6

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5859. Min Act: -0.0000

Data Index: 1210448 (The Pile)

Max Activating Token Index: 565

Text #7

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5647. Min Act: -0.0000

Data Index: 1251741 (The Pile)

Max Activating Token Index: 831

Text #8

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5609. Min Act: -0.0000

Data Index: 1590307 (The Pile)

Max Activating Token Index: 504

Text #9

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5883. Min Act: -0.0000

Data Index: 1656607 (The Pile)

Max Activating Token Index: 585

Text #10

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5748. Min Act: -0.0000

Data Index: 1329436 (The Pile)

Max Activating Token Index: 373

Text #11

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5559. Min Act: -0.0000

Data Index: 1721838 (The Pile)

Max Activating Token Index: 508

Text #12

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5416. Min Act: -0.0000

Data Index: 1824211 (The Pile)

Max Activating Token Index: 498

Text #13

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5327. Min Act: -0.0000

Data Index: 120068 (The Pile)

Max Activating Token Index: 425

Text #14

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5123. Min Act: -0.0000

Data Index: 100670 (The Pile)

Max Activating Token Index: 613

Text #15

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5103. Min Act: -0.0000

Data Index: 545947 (The Pile)

Max Activating Token Index: 763

Text #16

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1317204 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4941. Min Act: -0.0000

Data Index: 1545650 (The Pile)

Max Activating Token Index: 671

Text #18

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1281796 (The Pile)

Max Activating Token Index: 398

Text #19

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1938767 (The Pile)

Max Activating Token Index: 734