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

Dataset: The Pile

Neuron 4746 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.9921. Min Act: -0.0000

Data Index: 1922410 (The Pile)

Max Activating Token Index: 661

Text #1

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.9785. Min Act: -0.0000

Data Index: 886056 (The Pile)

Max Activating Token Index: 872

Text #2

Max Range: 1.0202. Min Range: -1.0202

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1811465 (The Pile)

Max Activating Token Index: 834

Text #3

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8585. Min Act: -0.0001

Data Index: 1096719 (The Pile)

Max Activating Token Index: 869

Text #4

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.9723. Min Act: -0.0000

Data Index: 1625856 (The Pile)

Max Activating Token Index: 649

Text #5

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8508. Min Act: -0.0000

Data Index: 1540567 (The Pile)

Max Activating Token Index: 1012

Text #6

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8463. Min Act: -0.0001

Data Index: 678914 (The Pile)

Max Activating Token Index: 188

Text #7

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8424. Min Act: -0.0000

Data Index: 1703009 (The Pile)

Max Activating Token Index: 615

Text #8

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1235034 (The Pile)

Max Activating Token Index: 884

Text #9

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8453. Min Act: -0.0000

Data Index: 299559 (The Pile)

Max Activating Token Index: 83

Text #10

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8532. Min Act: -0.0000

Data Index: 1900214 (The Pile)

Max Activating Token Index: 809

Text #11

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1865276 (The Pile)

Max Activating Token Index: 373

Text #12

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8907. Min Act: -0.0001

Data Index: 57590 (The Pile)

Max Activating Token Index: 947

Text #13

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1985706 (The Pile)

Max Activating Token Index: 832

Text #14

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8200. Min Act: -0.0000

Data Index: 671462 (The Pile)

Max Activating Token Index: 340

Text #15

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7651. Min Act: -0.0001

Data Index: 1398095 (The Pile)

Max Activating Token Index: 460

Text #16

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8699. Min Act: -0.0001

Data Index: 232702 (The Pile)

Max Activating Token Index: 524

Text #17

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1559358 (The Pile)

Max Activating Token Index: 362

Text #18

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8241. Min Act: -0.0001

Data Index: 1586284 (The Pile)

Max Activating Token Index: 216

Text #19

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7939. Min Act: -0.0000

Data Index: 61134 (The Pile)

Max Activating Token Index: 736