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

Dataset: The Pile

Neuron 2871 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: 1.7998. Min Range: -1.7998

Max Act: 1.7998. Min Act: -0.0000

Data Index: 354964 (The Pile)

Max Activating Token Index: 725

Text #1

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.6461. Min Act: -0.0000

Data Index: 1116647 (The Pile)

Max Activating Token Index: 40

Text #2

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.3800. Min Act: -0.0000

Data Index: 640455 (The Pile)

Max Activating Token Index: 287

Text #3

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.4149. Min Act: -0.0000

Data Index: 1281550 (The Pile)

Max Activating Token Index: 266

Text #4

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.2548. Min Act: -0.0000

Data Index: 225377 (The Pile)

Max Activating Token Index: 656

Text #5

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.1113. Min Act: -0.0000

Data Index: 168210 (The Pile)

Max Activating Token Index: 284

Text #6

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.3627. Min Act: -0.0000

Data Index: 917282 (The Pile)

Max Activating Token Index: 552

Text #7

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.2356. Min Act: -0.0000

Data Index: 856423 (The Pile)

Max Activating Token Index: 3

Text #8

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.3039. Min Act: -0.0000

Data Index: 171658 (The Pile)

Max Activating Token Index: 703

Text #9

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.1810. Min Act: -0.0000

Data Index: 1601890 (The Pile)

Max Activating Token Index: 785

Text #10

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.1440. Min Act: -0.0000

Data Index: 1783532 (The Pile)

Max Activating Token Index: 74

Text #11

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.2001. Min Act: -0.0000

Data Index: 473726 (The Pile)

Max Activating Token Index: 775

Text #12

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.1702. Min Act: -0.0000

Data Index: 437010 (The Pile)

Max Activating Token Index: 450

Text #13

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.2300. Min Act: -0.0000

Data Index: 915239 (The Pile)

Max Activating Token Index: 944

Text #14

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.1819. Min Act: -0.0000

Data Index: 394400 (The Pile)

Max Activating Token Index: 191

Text #15

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.1622. Min Act: -0.0000

Data Index: 985207 (The Pile)

Max Activating Token Index: 789

Text #16

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.2145. Min Act: -0.0000

Data Index: 1656632 (The Pile)

Max Activating Token Index: 146

Text #17

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.2067. Min Act: -0.0000

Data Index: 298779 (The Pile)

Max Activating Token Index: 413

Text #18

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.1746. Min Act: -0.0000

Data Index: 1232087 (The Pile)

Max Activating Token Index: 219

Text #19

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.1633. Min Act: -0.0000

Data Index: 1254302 (The Pile)

Max Activating Token Index: 94