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

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

Neuron 2101 in Layer 0

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: 0.0597. Min Act: -0.0002

Data Index: 160181 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0609. Min Act: -0.0002

Data Index: 809020 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0586. Min Act: -0.0002

Data Index: 620688 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0572. Min Act: -0.0001

Data Index: 96034 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0558. Min Act: -0.0002

Data Index: 445732 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0544. Min Act: -0.0002

Data Index: 753943 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0542. Min Act: -0.0002

Data Index: 394865 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0494. Min Act: -0.0002

Data Index: 724160 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0508. Min Act: -0.0002

Data Index: 607590 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0508. Min Act: -0.0002

Data Index: 810768 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0506. Min Act: -0.0002

Data Index: 394807 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0485. Min Act: -0.0002

Data Index: 313458 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1077225 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0495. Min Act: -0.0002

Data Index: 326438 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1273431 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0487. Min Act: -0.0002

Data Index: 530069 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0486. Min Act: -0.0002

Data Index: 529435 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0481. Min Act: -0.0002

Data Index: 140346 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0478. Min Act: -0.0002

Data Index: 672470 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0478. Min Act: -0.0002

Data Index: 97840 (C4 (Web Text))

Max Activating Token Index: 368