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

Dataset: The Pile

Neuron 1965 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2340. Min Range: -1.2340

Max Act: 1.2340. Min Act: -0.0000

Data Index: 580413 (The Pile)

Max Activating Token Index: 497

Text #1

Max Range: 1.2340. Min Range: -1.2340

Max Act: 1.1065. Min Act: -0.0000

Data Index: 1726210 (The Pile)

Max Activating Token Index: 88

Text #2

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9727. Min Act: -0.0000

Data Index: 621621 (The Pile)

Max Activating Token Index: 877

Text #3

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9615. Min Act: -0.0000

Data Index: 177161 (The Pile)

Max Activating Token Index: 877

Text #4

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9507. Min Act: -0.0000

Data Index: 998640 (The Pile)

Max Activating Token Index: 601

Text #5

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8212. Min Act: -0.0000

Data Index: 571397 (The Pile)

Max Activating Token Index: 737

Text #6

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8118. Min Act: -0.0000

Data Index: 1379177 (The Pile)

Max Activating Token Index: 594

Text #7

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8707. Min Act: -0.0000

Data Index: 1243386 (The Pile)

Max Activating Token Index: 879

Text #8

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8476. Min Act: -0.0000

Data Index: 1323164 (The Pile)

Max Activating Token Index: 549

Text #9

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8245. Min Act: -0.0000

Data Index: 340603 (The Pile)

Max Activating Token Index: 262

Text #10

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8335. Min Act: -0.0000

Data Index: 737860 (The Pile)

Max Activating Token Index: 457

Text #11

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1117580 (The Pile)

Max Activating Token Index: 676

Text #12

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8777. Min Act: -0.0000

Data Index: 1811188 (The Pile)

Max Activating Token Index: 293

Text #13

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8223. Min Act: -0.0000

Data Index: 1701116 (The Pile)

Max Activating Token Index: 229

Text #14

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8243. Min Act: -0.0000

Data Index: 148 (The Pile)

Max Activating Token Index: 887

Text #15

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.7936. Min Act: -0.0000

Data Index: 1338672 (The Pile)

Max Activating Token Index: 861

Text #16

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8404. Min Act: -0.0000

Data Index: 874678 (The Pile)

Max Activating Token Index: 903

Text #17

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1668091 (The Pile)

Max Activating Token Index: 995

Text #18

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8188. Min Act: -0.0000

Data Index: 926298 (The Pile)

Max Activating Token Index: 620

Text #19

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8222. Min Act: -0.0000

Data Index: 1632845 (The Pile)

Max Activating Token Index: 542