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

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

Neuron 3477 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0002

Data Index: 447406 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0288. Min Act: -0.0002

Data Index: 622243 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0283. Min Act: -0.0002

Data Index: 534196 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1215532 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0274. Min Act: -0.0002

Data Index: 548730 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0270. Min Act: -0.0002

Data Index: 798641 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0267. Min Act: -0.0002

Data Index: 150074 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0259. Min Act: -0.0002

Data Index: 848909 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0267. Min Act: -0.0002

Data Index: 408064 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0249. Min Act: -0.0002

Data Index: 895760 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1056595 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0252. Min Act: -0.0002

Data Index: 649978 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0250. Min Act: -0.0002

Data Index: 343764 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0249. Min Act: -0.0002

Data Index: 358003 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0252. Min Act: -0.0002

Data Index: 37214 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1244923 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0253. Min Act: -0.0002

Data Index: 573908 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0237. Min Act: -0.0002

Data Index: 438152 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0241. Min Act: -0.0002

Data Index: 28466 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0240. Min Act: -0.0002

Data Index: 947945 (C4 (Web Text))

Max Activating Token Index: 659