Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2282 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1281. Min Act: -0.0000

Data Index: 1177446 (The Pile)

Max Activating Token Index: 109

Text #1

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1323. Min Act: -0.0000

Data Index: 893608 (The Pile)

Max Activating Token Index: 19

Text #2

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1311. Min Act: -0.0000

Data Index: 389230 (The Pile)

Max Activating Token Index: 242

Text #3

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1309. Min Act: -0.0001

Data Index: 1197902 (The Pile)

Max Activating Token Index: 323

Text #4

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1253. Min Act: -0.0000

Data Index: 1826505 (The Pile)

Max Activating Token Index: 924

Text #5

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1247. Min Act: -0.0000

Data Index: 1480837 (The Pile)

Max Activating Token Index: 159

Text #6

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1234. Min Act: -0.0000

Data Index: 341818 (The Pile)

Max Activating Token Index: 492

Text #7

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1669689 (The Pile)

Max Activating Token Index: 246

Text #8

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1199. Min Act: -0.0000

Data Index: 562113 (The Pile)

Max Activating Token Index: 592

Text #9

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1229. Min Act: -0.0000

Data Index: 1446622 (The Pile)

Max Activating Token Index: 95

Text #10

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1262113 (The Pile)

Max Activating Token Index: 22

Text #11

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1219. Min Act: -0.0001

Data Index: 688299 (The Pile)

Max Activating Token Index: 445

Text #12

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1928900 (The Pile)

Max Activating Token Index: 93

Text #13

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1186. Min Act: -0.0000

Data Index: 1290584 (The Pile)

Max Activating Token Index: 953

Text #14

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1282. Min Act: -0.0000

Data Index: 173316 (The Pile)

Max Activating Token Index: 447

Text #15

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1252. Min Act: -0.0001

Data Index: 1687891 (The Pile)

Max Activating Token Index: 281

Text #16

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1201. Min Act: -0.0000

Data Index: 419785 (The Pile)

Max Activating Token Index: 670

Text #17

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1135. Min Act: -0.0000

Data Index: 763004 (The Pile)

Max Activating Token Index: 856

Text #18

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1196. Min Act: -0.0000

Data Index: 1856863 (The Pile)

Max Activating Token Index: 449

Text #19

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1160. Min Act: -0.0001

Data Index: 1062345 (The Pile)

Max Activating Token Index: 488