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

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

Neuron 3566 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.7030. Min Act: -0.0000

Data Index: 354040 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.7243. Min Act: -0.0000

Data Index: 432171 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1224421 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6797. Min Act: -0.0000

Data Index: 116258 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6867. Min Act: -0.0000

Data Index: 582830 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6553. Min Act: -0.0000

Data Index: 639423 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6363. Min Act: -0.0000

Data Index: 366087 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6293. Min Act: -0.0000

Data Index: 356187 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6190. Min Act: -0.0000

Data Index: 546740 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6042. Min Act: -0.0000

Data Index: 976322 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5982. Min Act: -0.0000

Data Index: 372696 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1007135 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1235728 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5944. Min Act: -0.0000

Data Index: 449298 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5943. Min Act: -0.0000

Data Index: 720851 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5952. Min Act: -0.0000

Data Index: 165281 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5857. Min Act: -0.0000

Data Index: 384239 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5682. Min Act: -0.0000

Data Index: 823108 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1178873 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5677. Min Act: -0.0000

Data Index: 320096 (C4 (Web Text))

Max Activating Token Index: 441