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

Dataset: The Pile

Neuron 2830 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1310. Min Range: -1.1310

Max Act: 1.1310. Min Act: -0.0000

Data Index: 452780 (The Pile)

Max Activating Token Index: 363

Text #1

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9923. Min Act: -0.0000

Data Index: 827613 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 1.1310. Min Range: -1.1310

Max Act: 1.0014. Min Act: -0.0000

Data Index: 380274 (The Pile)

Max Activating Token Index: 1010

Text #3

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9939. Min Act: -0.0000

Data Index: 1860709 (The Pile)

Max Activating Token Index: 519

Text #4

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1505048 (The Pile)

Max Activating Token Index: 458

Text #5

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9043. Min Act: -0.0000

Data Index: 200615 (The Pile)

Max Activating Token Index: 647

Text #6

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8440. Min Act: -0.0000

Data Index: 1522748 (The Pile)

Max Activating Token Index: 216

Text #7

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1650296 (The Pile)

Max Activating Token Index: 825

Text #8

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8632. Min Act: -0.0000

Data Index: 1102620 (The Pile)

Max Activating Token Index: 947

Text #9

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.7619. Min Act: -0.0000

Data Index: 857318 (The Pile)

Max Activating Token Index: 820

Text #10

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8776. Min Act: -0.0000

Data Index: 1996980 (The Pile)

Max Activating Token Index: 466

Text #11

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8005. Min Act: -0.0000

Data Index: 1822706 (The Pile)

Max Activating Token Index: 112

Text #12

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8161. Min Act: -0.0000

Data Index: 1332706 (The Pile)

Max Activating Token Index: 249

Text #13

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8714. Min Act: -0.0000

Data Index: 504330 (The Pile)

Max Activating Token Index: 319

Text #14

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.7696. Min Act: -0.0000

Data Index: 1013759 (The Pile)

Max Activating Token Index: 557

Text #15

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8666. Min Act: -0.0000

Data Index: 1636574 (The Pile)

Max Activating Token Index: 180

Text #16

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.7907. Min Act: -0.0000

Data Index: 531860 (The Pile)

Max Activating Token Index: 636

Text #17

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8014. Min Act: -0.0000

Data Index: 506940 (The Pile)

Max Activating Token Index: 154

Text #18

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1542100 (The Pile)

Max Activating Token Index: 295

Text #19

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8255. Min Act: -0.0000

Data Index: 1028073 (The Pile)

Max Activating Token Index: 23