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

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

Neuron 1922 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0602. Min Act: -0.0003

Data Index: 375568 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0609. Min Act: -0.0003

Data Index: 913470 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0588. Min Act: -0.0003

Data Index: 1157918 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0581. Min Act: -0.0003

Data Index: 34276 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0548. Min Act: -0.0003

Data Index: 1002144 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0532. Min Act: -0.0003

Data Index: 226992 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0511. Min Act: -0.0003

Data Index: 1078930 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0530. Min Act: -0.0003

Data Index: 499122 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0512. Min Act: -0.0003

Data Index: 511551 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0527. Min Act: -0.0003

Data Index: 920939 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0517. Min Act: -0.0003

Data Index: 144145 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0512. Min Act: -0.0003

Data Index: 1118980 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1239370 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0504. Min Act: -0.0002

Data Index: 962059 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0485. Min Act: -0.0002

Data Index: 1081073 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1185349 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0491. Min Act: -0.0003

Data Index: 792019 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0497. Min Act: -0.0003

Data Index: 98110 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0487. Min Act: -0.0003

Data Index: 867421 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0486. Min Act: -0.0003

Data Index: 885303 (C4 (Web Text))

Max Activating Token Index: 400