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

Dataset: The Pile

Neuron 1145 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6763. Min Range: -1.6763

Max Act: 1.3414. Min Act: -0.0000

Data Index: 855779 (The Pile)

Max Activating Token Index: 983

Text #1

Max Range: 1.6763. Min Range: -1.6763

Max Act: 1.6763. Min Act: -0.0000

Data Index: 1946114 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 1.6763. Min Range: -1.6763

Max Act: 1.3319. Min Act: -0.0000

Data Index: 1244827 (The Pile)

Max Activating Token Index: 466

Text #3

Max Range: 1.6763. Min Range: -1.6763

Max Act: 1.1640. Min Act: -0.0000

Data Index: 910779 (The Pile)

Max Activating Token Index: 736

Text #4

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.9253. Min Act: -0.0000

Data Index: 318420 (The Pile)

Max Activating Token Index: 734

Text #5

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.7926. Min Act: -0.0000

Data Index: 1179746 (The Pile)

Max Activating Token Index: 798

Text #6

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.8913. Min Act: -0.0000

Data Index: 477213 (The Pile)

Max Activating Token Index: 834

Text #7

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.9388. Min Act: -0.0000

Data Index: 1080635 (The Pile)

Max Activating Token Index: 517

Text #8

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.7524. Min Act: -0.0000

Data Index: 691404 (The Pile)

Max Activating Token Index: 389

Text #9

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.7293. Min Act: -0.0000

Data Index: 1577419 (The Pile)

Max Activating Token Index: 864

Text #10

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.7232. Min Act: -0.0000

Data Index: 1730416 (The Pile)

Max Activating Token Index: 506

Text #11

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.6670. Min Act: -0.0000

Data Index: 1642654 (The Pile)

Max Activating Token Index: 390

Text #12

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.7415. Min Act: -0.0000

Data Index: 594930 (The Pile)

Max Activating Token Index: 687

Text #13

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1067516 (The Pile)

Max Activating Token Index: 840

Text #14

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.7187. Min Act: -0.0000

Data Index: 1656365 (The Pile)

Max Activating Token Index: 272

Text #15

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.6835. Min Act: -0.0000

Data Index: 984885 (The Pile)

Max Activating Token Index: 550

Text #16

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.6082. Min Act: -0.0000

Data Index: 176157 (The Pile)

Max Activating Token Index: 202

Text #17

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.6107. Min Act: -0.0000

Data Index: 1706191 (The Pile)

Max Activating Token Index: 460

Text #18

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.6105. Min Act: -0.0000

Data Index: 772889 (The Pile)

Max Activating Token Index: 929

Text #19

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.6193. Min Act: -0.0000

Data Index: 848656 (The Pile)

Max Activating Token Index: 626