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

Dataset: The Pile

Neuron 2177 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: 1.1401. Min Range: -1.1401

Max Act: 1.1401. Min Act: -0.0000

Data Index: 1840061 (The Pile)

Max Activating Token Index: 286

Text #1

Max Range: 1.1401. Min Range: -1.1401

Max Act: 1.1401. Min Act: -0.0000

Data Index: 195733 (The Pile)

Max Activating Token Index: 688

Text #2

Max Range: 1.1401. Min Range: -1.1401

Max Act: 1.0946. Min Act: -0.0000

Data Index: 222700 (The Pile)

Max Activating Token Index: 627

Text #3

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.9896. Min Act: -0.0000

Data Index: 511675 (The Pile)

Max Activating Token Index: 522

Text #4

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.9393. Min Act: -0.0000

Data Index: 1229425 (The Pile)

Max Activating Token Index: 834

Text #5

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.9773. Min Act: -0.0000

Data Index: 1310811 (The Pile)

Max Activating Token Index: 1013

Text #6

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.9601. Min Act: -0.0000

Data Index: 1896100 (The Pile)

Max Activating Token Index: 821

Text #7

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.9058. Min Act: -0.0000

Data Index: 265921 (The Pile)

Max Activating Token Index: 308

Text #8

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.9562. Min Act: -0.0000

Data Index: 1391384 (The Pile)

Max Activating Token Index: 66

Text #9

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8573. Min Act: -0.0000

Data Index: 1755295 (The Pile)

Max Activating Token Index: 198

Text #10

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8804. Min Act: -0.0000

Data Index: 314171 (The Pile)

Max Activating Token Index: 251

Text #11

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8784. Min Act: -0.0000

Data Index: 526746 (The Pile)

Max Activating Token Index: 481

Text #12

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8361. Min Act: -0.0000

Data Index: 1123053 (The Pile)

Max Activating Token Index: 859

Text #13

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8678. Min Act: -0.0000

Data Index: 690006 (The Pile)

Max Activating Token Index: 960

Text #14

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8555. Min Act: -0.0000

Data Index: 578519 (The Pile)

Max Activating Token Index: 435

Text #15

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8309. Min Act: -0.0000

Data Index: 1590737 (The Pile)

Max Activating Token Index: 546

Text #16

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8569. Min Act: -0.0000

Data Index: 1610165 (The Pile)

Max Activating Token Index: 357

Text #17

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8707. Min Act: -0.0000

Data Index: 328358 (The Pile)

Max Activating Token Index: 137

Text #18

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8411. Min Act: -0.0000

Data Index: 465936 (The Pile)

Max Activating Token Index: 367

Text #19

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8434. Min Act: -0.0000

Data Index: 1279085 (The Pile)

Max Activating Token Index: 986