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

Dataset: The Pile

Neuron 3729 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: 1.0615. Min Range: -1.0615

Max Act: 0.9230. Min Act: -0.0000

Data Index: 1208797 (The Pile)

Max Activating Token Index: 701

Text #1

Max Range: 1.0615. Min Range: -1.0615

Max Act: 1.0019. Min Act: -0.0000

Data Index: 1141098 (The Pile)

Max Activating Token Index: 213

Text #2

Max Range: 1.0615. Min Range: -1.0615

Max Act: 1.0615. Min Act: -0.0000

Data Index: 1068468 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 1.0615. Min Range: -1.0615

Max Act: 1.0001. Min Act: -0.0000

Data Index: 1722859 (The Pile)

Max Activating Token Index: 205

Text #4

Max Range: 1.0615. Min Range: -1.0615

Max Act: 0.9431. Min Act: -0.0000

Data Index: 542963 (The Pile)

Max Activating Token Index: 992

Text #5

Max Range: 1.0615. Min Range: -1.0615

Max Act: 0.9260. Min Act: -0.0000

Data Index: 932480 (The Pile)

Max Activating Token Index: 113

Text #6

Max Range: 1.0615. Min Range: -1.0615

Max Act: 0.8980. Min Act: -0.0000

Data Index: 885599 (The Pile)

Max Activating Token Index: 126

Text #7

Max Range: 1.0615. Min Range: -1.0615

Max Act: 0.9439. Min Act: -0.0000

Data Index: 663461 (The Pile)

Max Activating Token Index: 9

Text #8

Max Range: 1.0615. Min Range: -1.0615

Max Act: 0.8320. Min Act: -0.0000

Data Index: 554116 (The Pile)

Max Activating Token Index: 326

Text #9

Max Range: 1.0615. Min Range: -1.0615

Max Act: 0.8491. Min Act: -0.0000

Data Index: 69547 (The Pile)

Max Activating Token Index: 64

Text #10

Max Range: 1.0615. Min Range: -1.0615

Max Act: 0.9357. Min Act: -0.0000

Data Index: 836827 (The Pile)

Max Activating Token Index: 500

Text #11

Max Range: 1.0615. Min Range: -1.0615

Max Act: 0.9049. Min Act: -0.0000

Data Index: 609206 (The Pile)

Max Activating Token Index: 640

Text #12

Max Range: 1.0615. Min Range: -1.0615

Max Act: 0.9290. Min Act: -0.0000

Data Index: 233154 (The Pile)

Max Activating Token Index: 454

Text #13

Max Range: 1.0615. Min Range: -1.0615

Max Act: 0.8440. Min Act: -0.0000

Data Index: 1086892 (The Pile)

Max Activating Token Index: 286

Text #14

Max Range: 1.0615. Min Range: -1.0615

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1803469 (The Pile)

Max Activating Token Index: 458

Text #15

Max Range: 1.0615. Min Range: -1.0615

Max Act: 0.8918. Min Act: -0.0000

Data Index: 221035 (The Pile)

Max Activating Token Index: 514

Text #16

Max Range: 1.0615. Min Range: -1.0615

Max Act: 0.8577. Min Act: -0.0000

Data Index: 1875621 (The Pile)

Max Activating Token Index: 202

Text #17

Max Range: 1.0615. Min Range: -1.0615

Max Act: 0.9079. Min Act: -0.0000

Data Index: 167416 (The Pile)

Max Activating Token Index: 345

Text #18

Max Range: 1.0615. Min Range: -1.0615

Max Act: 0.9231. Min Act: -0.0000

Data Index: 963157 (The Pile)

Max Activating Token Index: 523

Text #19

Max Range: 1.0615. Min Range: -1.0615

Max Act: 0.8736. Min Act: -0.0000

Data Index: 148535 (The Pile)

Max Activating Token Index: 104