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

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

Neuron 2336 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0318. Min Act: -0.0004

Data Index: 790549 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0306. Min Act: -0.0004

Data Index: 418865 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0320. Min Act: -0.0004

Data Index: 836583 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0300. Min Act: -0.0004

Data Index: 867971 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0284. Min Act: -0.0004

Data Index: 234435 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0288. Min Act: -0.0004

Data Index: 1253136 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0285. Min Act: -0.0004

Data Index: 1264435 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0284. Min Act: -0.0004

Data Index: 14038 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0296. Min Act: -0.0004

Data Index: 672036 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0281. Min Act: -0.0004

Data Index: 508834 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0295. Min Act: -0.0004

Data Index: 1069174 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0287. Min Act: -0.0004

Data Index: 1091948 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0270. Min Act: -0.0004

Data Index: 1333876 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0292. Min Act: -0.0004

Data Index: 1065374 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0262. Min Act: -0.0004

Data Index: 336913 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0263. Min Act: -0.0004

Data Index: 1015196 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0272. Min Act: -0.0004

Data Index: 1596370 (Python Code)

Max Activating Token Index: 738

Text #17

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0278. Min Act: -0.0004

Data Index: 1150057 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0272. Min Act: -0.0004

Data Index: 626053 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0275. Min Act: -0.0004

Data Index: 406266 (C4 (Web Text))

Max Activating Token Index: 72