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

Dataset: The Pile

Neuron 289 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1263. Min Range: -1.1263

Max Act: 1.1263. Min Act: -0.0000

Data Index: 864445 (The Pile)

Max Activating Token Index: 468

Text #1

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.9987. Min Act: -0.0000

Data Index: 1309212 (The Pile)

Max Activating Token Index: 365

Text #2

Max Range: 1.1263. Min Range: -1.1263

Max Act: 1.0463. Min Act: -0.0000

Data Index: 652346 (The Pile)

Max Activating Token Index: 647

Text #3

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.9840. Min Act: -0.0000

Data Index: 1235044 (The Pile)

Max Activating Token Index: 643

Text #4

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.8979. Min Act: -0.0000

Data Index: 746691 (The Pile)

Max Activating Token Index: 549

Text #5

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.8338. Min Act: -0.0000

Data Index: 1765767 (The Pile)

Max Activating Token Index: 500

Text #6

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.7169. Min Act: -0.0000

Data Index: 736103 (The Pile)

Max Activating Token Index: 681

Text #7

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.7641. Min Act: -0.0000

Data Index: 660420 (The Pile)

Max Activating Token Index: 162

Text #8

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.8155. Min Act: -0.0000

Data Index: 575808 (The Pile)

Max Activating Token Index: 287

Text #9

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.7336. Min Act: -0.0000

Data Index: 1692863 (The Pile)

Max Activating Token Index: 165

Text #10

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.6962. Min Act: -0.0000

Data Index: 1519398 (The Pile)

Max Activating Token Index: 299

Text #11

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1170718 (The Pile)

Max Activating Token Index: 171

Text #12

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.7147. Min Act: -0.0000

Data Index: 83856 (The Pile)

Max Activating Token Index: 458

Text #13

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.6583. Min Act: -0.0000

Data Index: 1168719 (The Pile)

Max Activating Token Index: 644

Text #14

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.7404. Min Act: -0.0000

Data Index: 127994 (The Pile)

Max Activating Token Index: 318

Text #15

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.7284. Min Act: -0.0000

Data Index: 771357 (The Pile)

Max Activating Token Index: 704

Text #16

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.6901. Min Act: -0.0000

Data Index: 1509082 (The Pile)

Max Activating Token Index: 36

Text #17

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.6795. Min Act: -0.0000

Data Index: 736356 (The Pile)

Max Activating Token Index: 417

Text #18

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.6926. Min Act: -0.0000

Data Index: 542294 (The Pile)

Max Activating Token Index: 403

Text #19

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.5984. Min Act: -0.0000

Data Index: 168223 (The Pile)

Max Activating Token Index: 794