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

Dataset: The Pile

Neuron 1459 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: 1.3991. Min Range: -1.3991

Max Act: 1.3732. Min Act: -0.0000

Data Index: 1749976 (The Pile)

Max Activating Token Index: 631

Text #1

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.2848. Min Act: -0.0000

Data Index: 1516174 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.3991. Min Act: -0.0000

Data Index: 245733 (The Pile)

Max Activating Token Index: 1012

Text #3

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.2405. Min Act: -0.0000

Data Index: 977195 (The Pile)

Max Activating Token Index: 724

Text #4

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.2080. Min Act: -0.0000

Data Index: 785303 (The Pile)

Max Activating Token Index: 364

Text #5

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.2034. Min Act: -0.0000

Data Index: 1176468 (The Pile)

Max Activating Token Index: 695

Text #6

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.2399. Min Act: -0.0000

Data Index: 1445327 (The Pile)

Max Activating Token Index: 225

Text #7

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.1977. Min Act: -0.0000

Data Index: 542824 (The Pile)

Max Activating Token Index: 712

Text #8

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.1500. Min Act: -0.0000

Data Index: 1211439 (The Pile)

Max Activating Token Index: 161

Text #9

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.0443. Min Act: -0.0000

Data Index: 472787 (The Pile)

Max Activating Token Index: 864

Text #10

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.0391. Min Act: -0.0000

Data Index: 993149 (The Pile)

Max Activating Token Index: 188

Text #11

Max Range: 1.3991. Min Range: -1.3991

Max Act: 0.9695. Min Act: -0.0000

Data Index: 1796301 (The Pile)

Max Activating Token Index: 426

Text #12

Max Range: 1.3991. Min Range: -1.3991

Max Act: 0.9555. Min Act: -0.0000

Data Index: 668551 (The Pile)

Max Activating Token Index: 290

Text #13

Max Range: 1.3991. Min Range: -1.3991

Max Act: 0.9260. Min Act: -0.0000

Data Index: 417110 (The Pile)

Max Activating Token Index: 600

Text #14

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.0248. Min Act: -0.0000

Data Index: 1632770 (The Pile)

Max Activating Token Index: 314

Text #15

Max Range: 1.3991. Min Range: -1.3991

Max Act: 0.9793. Min Act: -0.0000

Data Index: 1718842 (The Pile)

Max Activating Token Index: 534

Text #16

Max Range: 1.3991. Min Range: -1.3991

Max Act: 0.9119. Min Act: -0.0000

Data Index: 423671 (The Pile)

Max Activating Token Index: 210

Text #17

Max Range: 1.3991. Min Range: -1.3991

Max Act: 0.9538. Min Act: -0.0000

Data Index: 1062389 (The Pile)

Max Activating Token Index: 213

Text #18

Max Range: 1.3991. Min Range: -1.3991

Max Act: 0.9328. Min Act: -0.0000

Data Index: 1403326 (The Pile)

Max Activating Token Index: 137

Text #19

Max Range: 1.3991. Min Range: -1.3991

Max Act: 0.8953. Min Act: -0.0000

Data Index: 584420 (The Pile)

Max Activating Token Index: 917