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

Dataset: The Pile

Neuron 2496 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: 1.2179. Min Range: -1.2179

Max Act: 1.2179. Min Act: -0.0000

Data Index: 1633269 (The Pile)

Max Activating Token Index: 361

Text #1

Max Range: 1.2179. Min Range: -1.2179

Max Act: 1.0481. Min Act: -0.0000

Data Index: 1230705 (The Pile)

Max Activating Token Index: 363

Text #2

Max Range: 1.2179. Min Range: -1.2179

Max Act: 1.0757. Min Act: -0.0000

Data Index: 1584799 (The Pile)

Max Activating Token Index: 498

Text #3

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.9678. Min Act: -0.0000

Data Index: 357321 (The Pile)

Max Activating Token Index: 589

Text #4

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1641320 (The Pile)

Max Activating Token Index: 1010

Text #5

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.9886. Min Act: -0.0000

Data Index: 903347 (The Pile)

Max Activating Token Index: 641

Text #6

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.9987. Min Act: -0.0000

Data Index: 1260948 (The Pile)

Max Activating Token Index: 499

Text #7

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.9126. Min Act: -0.0000

Data Index: 1291971 (The Pile)

Max Activating Token Index: 218

Text #8

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.8980. Min Act: -0.0000

Data Index: 194777 (The Pile)

Max Activating Token Index: 920

Text #9

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.8991. Min Act: -0.0000

Data Index: 1067257 (The Pile)

Max Activating Token Index: 222

Text #10

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.8904. Min Act: -0.0000

Data Index: 807345 (The Pile)

Max Activating Token Index: 591

Text #11

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.9187. Min Act: -0.0000

Data Index: 1577593 (The Pile)

Max Activating Token Index: 515

Text #12

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.8975. Min Act: -0.0000

Data Index: 213791 (The Pile)

Max Activating Token Index: 721

Text #13

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.9024. Min Act: -0.0000

Data Index: 900531 (The Pile)

Max Activating Token Index: 933

Text #14

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.8698. Min Act: -0.0000

Data Index: 1348361 (The Pile)

Max Activating Token Index: 992

Text #15

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.8328. Min Act: -0.0000

Data Index: 1133099 (The Pile)

Max Activating Token Index: 256

Text #16

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1592474 (The Pile)

Max Activating Token Index: 805

Text #17

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.8391. Min Act: -0.0000

Data Index: 272736 (The Pile)

Max Activating Token Index: 199

Text #18

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.8149. Min Act: -0.0000

Data Index: 1132571 (The Pile)

Max Activating Token Index: 491

Text #19

Max Range: 1.2179. Min Range: -1.2179

Max Act: 0.7890. Min Act: -0.0000

Data Index: 601564 (The Pile)

Max Activating Token Index: 142