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

Dataset: The Pile

Neuron 4210 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: 0.9101. Min Range: -0.9101

Max Act: 0.8452. Min Act: -0.0000

Data Index: 1045518 (The Pile)

Max Activating Token Index: 776

Text #1

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.9101. Min Act: -0.0000

Data Index: 1568005 (The Pile)

Max Activating Token Index: 282

Text #2

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.8568. Min Act: -0.0000

Data Index: 169185 (The Pile)

Max Activating Token Index: 250

Text #3

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.8137. Min Act: -0.0000

Data Index: 794577 (The Pile)

Max Activating Token Index: 558

Text #4

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.8152. Min Act: -0.0000

Data Index: 1035002 (The Pile)

Max Activating Token Index: 700

Text #5

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.8126. Min Act: -0.0000

Data Index: 551813 (The Pile)

Max Activating Token Index: 892

Text #6

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.7937. Min Act: -0.0000

Data Index: 1035693 (The Pile)

Max Activating Token Index: 84

Text #7

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.8463. Min Act: -0.0000

Data Index: 1875856 (The Pile)

Max Activating Token Index: 692

Text #8

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.7658. Min Act: -0.0000

Data Index: 1505401 (The Pile)

Max Activating Token Index: 427

Text #9

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.7582. Min Act: -0.0000

Data Index: 950603 (The Pile)

Max Activating Token Index: 916

Text #10

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1676316 (The Pile)

Max Activating Token Index: 912

Text #11

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.7104. Min Act: -0.0000

Data Index: 305446 (The Pile)

Max Activating Token Index: 605

Text #12

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.7283. Min Act: -0.0000

Data Index: 504227 (The Pile)

Max Activating Token Index: 831

Text #13

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.7500. Min Act: -0.0000

Data Index: 761857 (The Pile)

Max Activating Token Index: 210

Text #14

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.7232. Min Act: -0.0000

Data Index: 448173 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.7483. Min Act: -0.0000

Data Index: 1074909 (The Pile)

Max Activating Token Index: 1015

Text #16

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.7270. Min Act: -0.0000

Data Index: 1576429 (The Pile)

Max Activating Token Index: 917

Text #17

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.7574. Min Act: -0.0000

Data Index: 984059 (The Pile)

Max Activating Token Index: 867

Text #18

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1085308 (The Pile)

Max Activating Token Index: 334

Text #19

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.6839. Min Act: -0.0000

Data Index: 1061558 (The Pile)

Max Activating Token Index: 362