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

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

Neuron 3584 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: 0.0333. Min Range: -0.0333

Max Act: 0.0333. Min Act: -0.0002

Data Index: 725751 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0330. Min Act: -0.0002

Data Index: 1021046 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1305016 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1244318 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0262. Min Act: -0.0002

Data Index: 923023 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0261. Min Act: -0.0002

Data Index: 181946 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0268. Min Act: -0.0002

Data Index: 634474 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0268. Min Act: -0.0002

Data Index: 129032 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1071440 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0250. Min Act: -0.0002

Data Index: 817107 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0245. Min Act: -0.0002

Data Index: 34786 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0248. Min Act: -0.0002

Data Index: 996871 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1166996 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0245. Min Act: -0.0002

Data Index: 159609 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0249. Min Act: -0.0002

Data Index: 649872 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0241. Min Act: -0.0002

Data Index: 1075991 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0243. Min Act: -0.0002

Data Index: 66640 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0242. Min Act: -0.0002

Data Index: 600095 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0240. Min Act: -0.0002

Data Index: 688281 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0233. Min Act: -0.0002

Data Index: 919533 (C4 (Web Text))

Max Activating Token Index: 424