Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1618 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0748. Min Act: -0.0006

Data Index: 1145196 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0675. Min Act: -0.0005

Data Index: 1129021 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0650. Min Act: -0.0005

Data Index: 700721 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0575. Min Act: -0.0006

Data Index: 842314 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0570. Min Act: -0.0006

Data Index: 625470 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0582. Min Act: -0.0006

Data Index: 612072 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0552. Min Act: -0.0006

Data Index: 1178928 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0572. Min Act: -0.0005

Data Index: 826339 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0567. Min Act: -0.0006

Data Index: 602815 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0522. Min Act: -0.0006

Data Index: 1021681 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0565. Min Act: -0.0005

Data Index: 934890 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0517. Min Act: -0.0006

Data Index: 698046 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0580. Min Act: -0.0005

Data Index: 1171372 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0495. Min Act: -0.0006

Data Index: 461186 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0555. Min Act: -0.0006

Data Index: 1252650 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0552. Min Act: -0.0006

Data Index: 737255 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0530. Min Act: -0.0006

Data Index: 64131 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0507. Min Act: -0.0006

Data Index: 1072517 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0505. Min Act: -0.0006

Data Index: 266458 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0501. Min Act: -0.0006

Data Index: 1087996 (C4 (Web Text))

Max Activating Token Index: 552