Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4829 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1155483 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0294. Min Act: -0.0000

Data Index: 1254767 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0273. Min Act: -0.0000

Data Index: 392518 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0287. Min Act: -0.0000

Data Index: 1070713 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0238. Min Act: -0.0000

Data Index: 1023175 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0260. Min Act: -0.0000

Data Index: 681309 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0230. Min Act: -0.0000

Data Index: 781458 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0231. Min Act: -0.0000

Data Index: 752254 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0235. Min Act: -0.0000

Data Index: 254079 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0220. Min Act: -0.0000

Data Index: 142348 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0226. Min Act: -0.0000

Data Index: 921828 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0225. Min Act: -0.0000

Data Index: 397608 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0235. Min Act: -0.0000

Data Index: 1467816 (Python Code)

Max Activating Token Index: 281

Text #13

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0225. Min Act: -0.0000

Data Index: 7371 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0224. Min Act: -0.0000

Data Index: 1032027 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0224. Min Act: -0.0000

Data Index: 869243 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0216. Min Act: -0.0000

Data Index: 343626 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0211. Min Act: -0.0000

Data Index: 814968 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0250. Min Act: -0.0000

Data Index: 281168 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0217. Min Act: -0.0000

Data Index: 21738 (C4 (Web Text))

Max Activating Token Index: 748