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

Dataset: The Pile

Neuron 297 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.4794. Min Act: -0.0000

Data Index: 926953 (The Pile)

Max Activating Token Index: 565

Text #1

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.5689. Min Act: -0.0000

Data Index: 213160 (The Pile)

Max Activating Token Index: 453

Text #2

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.5185. Min Act: -0.0000

Data Index: 1630789 (The Pile)

Max Activating Token Index: 734

Text #3

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.2725. Min Act: -0.0000

Data Index: 1139786 (The Pile)

Max Activating Token Index: 512

Text #4

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.4144. Min Act: -0.0000

Data Index: 1698893 (The Pile)

Max Activating Token Index: 429

Text #5

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.3985. Min Act: -0.0000

Data Index: 1431201 (The Pile)

Max Activating Token Index: 874

Text #6

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.3351. Min Act: -0.0000

Data Index: 1691592 (The Pile)

Max Activating Token Index: 895

Text #7

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.3839. Min Act: -0.0000

Data Index: 1670196 (The Pile)

Max Activating Token Index: 400

Text #8

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.3466. Min Act: -0.0000

Data Index: 1309440 (The Pile)

Max Activating Token Index: 666

Text #9

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.2854. Min Act: -0.0000

Data Index: 1251359 (The Pile)

Max Activating Token Index: 579

Text #10

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.3050. Min Act: -0.0000

Data Index: 847890 (The Pile)

Max Activating Token Index: 398

Text #11

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.2804. Min Act: -0.0000

Data Index: 1256420 (The Pile)

Max Activating Token Index: 825

Text #12

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.2735. Min Act: -0.0000

Data Index: 1440311 (The Pile)

Max Activating Token Index: 766

Text #13

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.2144. Min Act: -0.0000

Data Index: 797003 (The Pile)

Max Activating Token Index: 625

Text #14

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.3122. Min Act: -0.0000

Data Index: 653826 (The Pile)

Max Activating Token Index: 491

Text #15

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.4545. Min Act: -0.0000

Data Index: 390857 (The Pile)

Max Activating Token Index: 710

Text #16

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.1978. Min Act: -0.0000

Data Index: 928468 (The Pile)

Max Activating Token Index: 905

Text #17

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.2293. Min Act: -0.0000

Data Index: 52118 (The Pile)

Max Activating Token Index: 388

Text #18

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.1035. Min Act: -0.0000

Data Index: 1713349 (The Pile)

Max Activating Token Index: 746

Text #19

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.1700. Min Act: -0.0000

Data Index: 639632 (The Pile)

Max Activating Token Index: 374