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

Dataset: The Pile

Neuron 4476 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.8682. Min Act: -0.0000

Data Index: 1862200 (The Pile)

Max Activating Token Index: 316

Text #1

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1023799 (The Pile)

Max Activating Token Index: 407

Text #2

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7924. Min Act: -0.0000

Data Index: 1427263 (The Pile)

Max Activating Token Index: 759

Text #3

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7681. Min Act: -0.0000

Data Index: 1870425 (The Pile)

Max Activating Token Index: 409

Text #4

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7457. Min Act: -0.0000

Data Index: 1340699 (The Pile)

Max Activating Token Index: 780

Text #5

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7197. Min Act: -0.0000

Data Index: 1430813 (The Pile)

Max Activating Token Index: 519

Text #6

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7244. Min Act: -0.0000

Data Index: 1114064 (The Pile)

Max Activating Token Index: 877

Text #7

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.6229. Min Act: -0.0000

Data Index: 419903 (The Pile)

Max Activating Token Index: 882

Text #8

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7471. Min Act: -0.0000

Data Index: 1370848 (The Pile)

Max Activating Token Index: 828

Text #9

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.6894. Min Act: -0.0000

Data Index: 1397277 (The Pile)

Max Activating Token Index: 282

Text #10

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.6812. Min Act: -0.0000

Data Index: 783616 (The Pile)

Max Activating Token Index: 974

Text #11

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1107292 (The Pile)

Max Activating Token Index: 51

Text #12

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.6710. Min Act: -0.0000

Data Index: 1397118 (The Pile)

Max Activating Token Index: 969

Text #13

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.5642. Min Act: -0.0000

Data Index: 525800 (The Pile)

Max Activating Token Index: 333

Text #14

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.6092. Min Act: -0.0000

Data Index: 931949 (The Pile)

Max Activating Token Index: 772

Text #15

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.6723. Min Act: -0.0000

Data Index: 109433 (The Pile)

Max Activating Token Index: 697

Text #16

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.6868. Min Act: -0.0000

Data Index: 1211025 (The Pile)

Max Activating Token Index: 835

Text #17

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.6589. Min Act: -0.0000

Data Index: 778123 (The Pile)

Max Activating Token Index: 428

Text #18

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.6705. Min Act: -0.0000

Data Index: 486246 (The Pile)

Max Activating Token Index: 206

Text #19

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.5928. Min Act: -0.0000

Data Index: 61650 (The Pile)

Max Activating Token Index: 739