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

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

Neuron 4822 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.8389. Min Act: 0.0001

Data Index: 351467 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.5065. Min Act: -0.0000

Data Index: 255762 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.4559. Min Act: -0.0000

Data Index: 219999 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.4641. Min Act: -0.0000

Data Index: 101605 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.4491. Min Act: 0.0000

Data Index: 1106983 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.4049. Min Act: 0.0000

Data Index: 201823 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.3682. Min Act: 0.0000

Data Index: 800479 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.3762. Min Act: 0.0000

Data Index: 925963 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.3841. Min Act: 0.0000

Data Index: 1273529 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.3782. Min Act: 0.0000

Data Index: 1227565 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.3775. Min Act: 0.0000

Data Index: 1239049 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.3615. Min Act: -0.0000

Data Index: 670293 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1556262 (Python Code)

Max Activating Token Index: 404

Text #13

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.3410. Min Act: 0.0000

Data Index: 564039 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.3591. Min Act: 0.0001

Data Index: 932337 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.3276. Min Act: 0.0000

Data Index: 744631 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.3553. Min Act: 0.0000

Data Index: 1234695 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1161262 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.3356. Min Act: -0.0000

Data Index: 578238 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.3544. Min Act: 0.0001

Data Index: 641545 (C4 (Web Text))

Max Activating Token Index: 201