Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4730 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.5401. Min Act: -0.0000

Data Index: 532848 (The Pile)

Max Activating Token Index: 707

Text #1

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.3847. Min Act: -0.0000

Data Index: 870076 (The Pile)

Max Activating Token Index: 526

Text #2

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.2785. Min Act: -0.0000

Data Index: 1871033 (The Pile)

Max Activating Token Index: 447

Text #3

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.0881. Min Act: -0.0000

Data Index: 952829 (The Pile)

Max Activating Token Index: 339

Text #4

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.2041. Min Act: -0.0000

Data Index: 1465259 (The Pile)

Max Activating Token Index: 578

Text #5

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.0353. Min Act: -0.0000

Data Index: 484576 (The Pile)

Max Activating Token Index: 435

Text #6

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.0932. Min Act: -0.0000

Data Index: 1509392 (The Pile)

Max Activating Token Index: 273

Text #7

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.0877. Min Act: -0.0000

Data Index: 611563 (The Pile)

Max Activating Token Index: 570

Text #8

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.0586. Min Act: -0.0000

Data Index: 397628 (The Pile)

Max Activating Token Index: 459

Text #9

Max Range: 1.5401. Min Range: -1.5401

Max Act: 0.9526. Min Act: -0.0000

Data Index: 948147 (The Pile)

Max Activating Token Index: 446

Text #10

Max Range: 1.5401. Min Range: -1.5401

Max Act: 0.9453. Min Act: -0.0000

Data Index: 1074076 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 1.5401. Min Range: -1.5401

Max Act: 0.9627. Min Act: -0.0000

Data Index: 337388 (The Pile)

Max Activating Token Index: 618

Text #12

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.0452. Min Act: -0.0000

Data Index: 1295377 (The Pile)

Max Activating Token Index: 702

Text #13

Max Range: 1.5401. Min Range: -1.5401

Max Act: 0.8978. Min Act: -0.0000

Data Index: 801453 (The Pile)

Max Activating Token Index: 922

Text #14

Max Range: 1.5401. Min Range: -1.5401

Max Act: 0.9992. Min Act: -0.0000

Data Index: 1432857 (The Pile)

Max Activating Token Index: 488

Text #15

Max Range: 1.5401. Min Range: -1.5401

Max Act: 0.9586. Min Act: -0.0000

Data Index: 932526 (The Pile)

Max Activating Token Index: 982

Text #16

Max Range: 1.5401. Min Range: -1.5401

Max Act: 0.9481. Min Act: -0.0000

Data Index: 459756 (The Pile)

Max Activating Token Index: 673

Text #17

Max Range: 1.5401. Min Range: -1.5401

Max Act: 0.9350. Min Act: -0.0000

Data Index: 1866107 (The Pile)

Max Activating Token Index: 308

Text #18

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.0150. Min Act: -0.0000

Data Index: 313292 (The Pile)

Max Activating Token Index: 282

Text #19

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1028261 (The Pile)

Max Activating Token Index: 935