Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1063 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0547. Min Range: -1.0547

Max Act: 1.0520. Min Act: -0.0000

Data Index: 414273 (The Pile)

Max Activating Token Index: 957

Text #1

Max Range: 1.0547. Min Range: -1.0547

Max Act: 1.0547. Min Act: -0.0000

Data Index: 643868 (The Pile)

Max Activating Token Index: 236

Text #2

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.9042. Min Act: -0.0000

Data Index: 1516854 (The Pile)

Max Activating Token Index: 123

Text #3

Max Range: 1.0547. Min Range: -1.0547

Max Act: 1.0002. Min Act: -0.0000

Data Index: 871139 (The Pile)

Max Activating Token Index: 351

Text #4

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.9363. Min Act: -0.0000

Data Index: 1364391 (The Pile)

Max Activating Token Index: 705

Text #5

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.9337. Min Act: -0.0000

Data Index: 360523 (The Pile)

Max Activating Token Index: 572

Text #6

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.9157. Min Act: -0.0000

Data Index: 896832 (The Pile)

Max Activating Token Index: 1020

Text #7

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.9673. Min Act: -0.0000

Data Index: 588385 (The Pile)

Max Activating Token Index: 409

Text #8

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.9649. Min Act: -0.0000

Data Index: 1571371 (The Pile)

Max Activating Token Index: 787

Text #9

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.9273. Min Act: -0.0000

Data Index: 764030 (The Pile)

Max Activating Token Index: 999

Text #10

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.8750. Min Act: -0.0000

Data Index: 1394909 (The Pile)

Max Activating Token Index: 567

Text #11

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.9801. Min Act: -0.0000

Data Index: 1678900 (The Pile)

Max Activating Token Index: 369

Text #12

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.9646. Min Act: -0.0000

Data Index: 1589554 (The Pile)

Max Activating Token Index: 670

Text #13

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.8697. Min Act: -0.0000

Data Index: 92512 (The Pile)

Max Activating Token Index: 804

Text #14

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.9287. Min Act: -0.0000

Data Index: 1562879 (The Pile)

Max Activating Token Index: 345

Text #15

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.8719. Min Act: -0.0000

Data Index: 781204 (The Pile)

Max Activating Token Index: 554

Text #16

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.8906. Min Act: -0.0000

Data Index: 1384100 (The Pile)

Max Activating Token Index: 521

Text #17

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.9253. Min Act: -0.0000

Data Index: 1207676 (The Pile)

Max Activating Token Index: 488

Text #18

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.8921. Min Act: -0.0000

Data Index: 1152415 (The Pile)

Max Activating Token Index: 772

Text #19

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.7824. Min Act: -0.0000

Data Index: 266405 (The Pile)

Max Activating Token Index: 759