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

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

Neuron 2763 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2471. Min Range: -1.2471

Max Act: 1.2471. Min Act: -0.0000

Data Index: 233218 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.8535. Min Act: -0.0001

Data Index: 1019138 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.8411. Min Act: -0.0000

Data Index: 590327 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.7661. Min Act: -0.0000

Data Index: 511449 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.7555. Min Act: -0.0000

Data Index: 186116 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.7184. Min Act: -0.0000

Data Index: 52002 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.7157. Min Act: -0.0001

Data Index: 423835 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.6870. Min Act: -0.0000

Data Index: 1020387 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.6743. Min Act: -0.0000

Data Index: 42110 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.6481. Min Act: -0.0000

Data Index: 139421 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.6880. Min Act: -0.0001

Data Index: 955936 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.6610. Min Act: -0.0000

Data Index: 741783 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.6406. Min Act: -0.0000

Data Index: 1138805 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.6626. Min Act: -0.0001

Data Index: 449419 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.6235. Min Act: -0.0000

Data Index: 570383 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.6694. Min Act: -0.0000

Data Index: 22196 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.6294. Min Act: -0.0001

Data Index: 1128388 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.6520. Min Act: -0.0000

Data Index: 709690 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.6085. Min Act: -0.0000

Data Index: 164805 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1124397 (C4 (Web Text))

Max Activating Token Index: 323