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

Dataset: The Pile

Neuron 3656 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: 0.8240. Min Range: -0.8240

Max Act: 0.8240. Min Act: -0.0000

Data Index: 921232 (The Pile)

Max Activating Token Index: 479

Text #1

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7909. Min Act: -0.0000

Data Index: 522663 (The Pile)

Max Activating Token Index: 391

Text #2

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6282. Min Act: -0.0000

Data Index: 144570 (The Pile)

Max Activating Token Index: 356

Text #3

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1615276 (The Pile)

Max Activating Token Index: 321

Text #4

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.5995. Min Act: -0.0000

Data Index: 672707 (The Pile)

Max Activating Token Index: 385

Text #5

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1653553 (The Pile)

Max Activating Token Index: 719

Text #6

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.4753. Min Act: -0.0000

Data Index: 214235 (The Pile)

Max Activating Token Index: 967

Text #7

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1458885 (The Pile)

Max Activating Token Index: 934

Text #8

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.4985. Min Act: -0.0000

Data Index: 834175 (The Pile)

Max Activating Token Index: 593

Text #9

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.5112. Min Act: -0.0000

Data Index: 1683562 (The Pile)

Max Activating Token Index: 338

Text #10

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.4404. Min Act: -0.0000

Data Index: 370295 (The Pile)

Max Activating Token Index: 483

Text #11

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.4761. Min Act: -0.0000

Data Index: 1781681 (The Pile)

Max Activating Token Index: 355

Text #12

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.4788. Min Act: -0.0000

Data Index: 74395 (The Pile)

Max Activating Token Index: 210

Text #13

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.3855. Min Act: -0.0000

Data Index: 212136 (The Pile)

Max Activating Token Index: 685

Text #14

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1825146 (The Pile)

Max Activating Token Index: 324

Text #15

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.4405. Min Act: -0.0000

Data Index: 1239458 (The Pile)

Max Activating Token Index: 94

Text #16

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1695361 (The Pile)

Max Activating Token Index: 228

Text #17

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1587765 (The Pile)

Max Activating Token Index: 463

Text #18

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1898396 (The Pile)

Max Activating Token Index: 453

Text #19

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1060199 (The Pile)

Max Activating Token Index: 259