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

Dataset: The Pile

Neuron 670 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8115. Min Range: -1.8115

Max Act: 1.7196. Min Act: -0.0000

Data Index: 545380 (The Pile)

Max Activating Token Index: 597

Text #1

Max Range: 1.8115. Min Range: -1.8115

Max Act: 1.7882. Min Act: -0.0000

Data Index: 714971 (The Pile)

Max Activating Token Index: 611

Text #2

Max Range: 1.8115. Min Range: -1.8115

Max Act: 1.6626. Min Act: -0.0000

Data Index: 164375 (The Pile)

Max Activating Token Index: 1012

Text #3

Max Range: 1.8115. Min Range: -1.8115

Max Act: 1.6185. Min Act: -0.0000

Data Index: 1457548 (The Pile)

Max Activating Token Index: 170

Text #4

Max Range: 1.8115. Min Range: -1.8115

Max Act: 1.8115. Min Act: -0.0000

Data Index: 1540578 (The Pile)

Max Activating Token Index: 326

Text #5

Max Range: 1.8115. Min Range: -1.8115

Max Act: 1.5329. Min Act: -0.0000

Data Index: 17314 (The Pile)

Max Activating Token Index: 472

Text #6

Max Range: 1.8115. Min Range: -1.8115

Max Act: 1.6945. Min Act: -0.0000

Data Index: 1581865 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 1.8115. Min Range: -1.8115

Max Act: 1.6598. Min Act: -0.0000

Data Index: 1683943 (The Pile)

Max Activating Token Index: 396

Text #8

Max Range: 1.8115. Min Range: -1.8115

Max Act: 1.5100. Min Act: -0.0000

Data Index: 535381 (The Pile)

Max Activating Token Index: 262

Text #9

Max Range: 1.8115. Min Range: -1.8115

Max Act: 1.4073. Min Act: -0.0000

Data Index: 718763 (The Pile)

Max Activating Token Index: 657

Text #10

Max Range: 1.8115. Min Range: -1.8115

Max Act: 1.4635. Min Act: -0.0000

Data Index: 1547937 (The Pile)

Max Activating Token Index: 301

Text #11

Max Range: 1.8115. Min Range: -1.8115

Max Act: 1.7196. Min Act: -0.0000

Data Index: 778176 (The Pile)

Max Activating Token Index: 553

Text #12

Max Range: 1.8115. Min Range: -1.8115

Max Act: 1.5540. Min Act: -0.0000

Data Index: 1282602 (The Pile)

Max Activating Token Index: 688

Text #13

Max Range: 1.8115. Min Range: -1.8115

Max Act: 1.6676. Min Act: -0.0000

Data Index: 475886 (The Pile)

Max Activating Token Index: 859

Text #14

Max Range: 1.8115. Min Range: -1.8115

Max Act: 1.5782. Min Act: -0.0000

Data Index: 174351 (The Pile)

Max Activating Token Index: 80

Text #15

Max Range: 1.8115. Min Range: -1.8115

Max Act: 1.4951. Min Act: -0.0000

Data Index: 853183 (The Pile)

Max Activating Token Index: 1012

Text #16

Max Range: 1.8115. Min Range: -1.8115

Max Act: 1.4951. Min Act: -0.0000

Data Index: 1670203 (The Pile)

Max Activating Token Index: 400

Text #17

Max Range: 1.8115. Min Range: -1.8115

Max Act: 1.4706. Min Act: -0.0000

Data Index: 1921864 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 1.8115. Min Range: -1.8115

Max Act: 1.5559. Min Act: -0.0000

Data Index: 1645557 (The Pile)

Max Activating Token Index: 315

Text #19

Max Range: 1.8115. Min Range: -1.8115

Max Act: 1.5467. Min Act: -0.0000

Data Index: 460622 (The Pile)

Max Activating Token Index: 291