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

Dataset: The Pile

Neuron 1424 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: 1.3452. Min Range: -1.3452

Max Act: 1.3452. Min Act: -0.0000

Data Index: 1808571 (The Pile)

Max Activating Token Index: 566

Text #1

Max Range: 1.3452. Min Range: -1.3452

Max Act: 0.9427. Min Act: -0.0000

Data Index: 1848239 (The Pile)

Max Activating Token Index: 363

Text #2

Max Range: 1.3452. Min Range: -1.3452

Max Act: 0.6413. Min Act: -0.0000

Data Index: 18025 (The Pile)

Max Activating Token Index: 512

Text #3

Max Range: 1.3452. Min Range: -1.3452

Max Act: 0.6230. Min Act: -0.0000

Data Index: 952920 (The Pile)

Max Activating Token Index: 174

Text #4

Max Range: 1.3452. Min Range: -1.3452

Max Act: 0.6063. Min Act: -0.0000

Data Index: 345529 (The Pile)

Max Activating Token Index: 491

Text #5

Max Range: 1.3452. Min Range: -1.3452

Max Act: 0.6029. Min Act: -0.0000

Data Index: 1935085 (The Pile)

Max Activating Token Index: 137

Text #6

Max Range: 1.3452. Min Range: -1.3452

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1299480 (The Pile)

Max Activating Token Index: 728

Text #7

Max Range: 1.3452. Min Range: -1.3452

Max Act: 0.4978. Min Act: -0.0000

Data Index: 975132 (The Pile)

Max Activating Token Index: 355

Text #8

Max Range: 1.3452. Min Range: -1.3452

Max Act: 0.5651. Min Act: -0.0000

Data Index: 119596 (The Pile)

Max Activating Token Index: 801

Text #9

Max Range: 1.3452. Min Range: -1.3452

Max Act: 0.5386. Min Act: -0.0000

Data Index: 1992723 (The Pile)

Max Activating Token Index: 536

Text #10

Max Range: 1.3452. Min Range: -1.3452

Max Act: 0.5404. Min Act: -0.0000

Data Index: 540814 (The Pile)

Max Activating Token Index: 984

Text #11

Max Range: 1.3452. Min Range: -1.3452

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1910191 (The Pile)

Max Activating Token Index: 253

Text #12

Max Range: 1.3452. Min Range: -1.3452

Max Act: 0.4988. Min Act: -0.0000

Data Index: 258597 (The Pile)

Max Activating Token Index: 399

Text #13

Max Range: 1.3452. Min Range: -1.3452

Max Act: 0.5029. Min Act: -0.0000

Data Index: 1930072 (The Pile)

Max Activating Token Index: 553

Text #14

Max Range: 1.3452. Min Range: -1.3452

Max Act: 0.5270. Min Act: -0.0000

Data Index: 654634 (The Pile)

Max Activating Token Index: 512

Text #15

Max Range: 1.3452. Min Range: -1.3452

Max Act: 0.5298. Min Act: -0.0000

Data Index: 795825 (The Pile)

Max Activating Token Index: 232

Text #16

Max Range: 1.3452. Min Range: -1.3452

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1550957 (The Pile)

Max Activating Token Index: 563

Text #17

Max Range: 1.3452. Min Range: -1.3452

Max Act: 0.5274. Min Act: -0.0000

Data Index: 1418710 (The Pile)

Max Activating Token Index: 869

Text #18

Max Range: 1.3452. Min Range: -1.3452

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1896830 (The Pile)

Max Activating Token Index: 681

Text #19

Max Range: 1.3452. Min Range: -1.3452

Max Act: 0.5025. Min Act: -0.0000

Data Index: 1525519 (The Pile)

Max Activating Token Index: 31