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

Dataset: The Pile

Neuron 2773 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.6292. Min Act: -0.0000

Data Index: 699061 (The Pile)

Max Activating Token Index: 606

Text #1

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.5508. Min Act: -0.0000

Data Index: 1814588 (The Pile)

Max Activating Token Index: 25

Text #2

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.5145. Min Act: -0.0000

Data Index: 974168 (The Pile)

Max Activating Token Index: 293

Text #3

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1998361 (The Pile)

Max Activating Token Index: 32

Text #4

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.5018. Min Act: -0.0000

Data Index: 325631 (The Pile)

Max Activating Token Index: 250

Text #5

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1669645 (The Pile)

Max Activating Token Index: 307

Text #6

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1633846 (The Pile)

Max Activating Token Index: 56

Text #7

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1019416 (The Pile)

Max Activating Token Index: 241

Text #8

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.5283. Min Act: -0.0000

Data Index: 540863 (The Pile)

Max Activating Token Index: 587

Text #9

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.4993. Min Act: -0.0000

Data Index: 531903 (The Pile)

Max Activating Token Index: 249

Text #10

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.5298. Min Act: -0.0000

Data Index: 1185494 (The Pile)

Max Activating Token Index: 483

Text #11

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1711015 (The Pile)

Max Activating Token Index: 459

Text #12

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.5223. Min Act: -0.0000

Data Index: 998522 (The Pile)

Max Activating Token Index: 523

Text #13

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1361686 (The Pile)

Max Activating Token Index: 338

Text #14

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.4984. Min Act: -0.0000

Data Index: 654954 (The Pile)

Max Activating Token Index: 105

Text #15

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.5253. Min Act: -0.0000

Data Index: 1086194 (The Pile)

Max Activating Token Index: 192

Text #16

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.5096. Min Act: -0.0000

Data Index: 442560 (The Pile)

Max Activating Token Index: 234

Text #17

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.4692. Min Act: -0.0000

Data Index: 1381456 (The Pile)

Max Activating Token Index: 61

Text #18

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.5095. Min Act: -0.0000

Data Index: 512512 (The Pile)

Max Activating Token Index: 331

Text #19

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.5042. Min Act: -0.0000

Data Index: 962927 (The Pile)

Max Activating Token Index: 191