Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3128 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0602. Min Range: -2.0602

Max Act: 2.0602. Min Act: -0.0000

Data Index: 481976 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 2.0602. Min Range: -2.0602

Max Act: 1.8281. Min Act: -0.0000

Data Index: 1022487 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 2.0602. Min Range: -2.0602

Max Act: 1.6547. Min Act: -0.0000

Data Index: 1102223 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 2.0602. Min Range: -2.0602

Max Act: 1.4749. Min Act: -0.0000

Data Index: 1198628 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 2.0602. Min Range: -2.0602

Max Act: 1.6776. Min Act: -0.0000

Data Index: 1175836 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 2.0602. Min Range: -2.0602

Max Act: 1.5841. Min Act: -0.0000

Data Index: 494399 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 2.0602. Min Range: -2.0602

Max Act: 1.4724. Min Act: -0.0000

Data Index: 465194 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 2.0602. Min Range: -2.0602

Max Act: 1.4827. Min Act: -0.0000

Data Index: 434871 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 2.0602. Min Range: -2.0602

Max Act: 1.4615. Min Act: -0.0001

Data Index: 324408 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 2.0602. Min Range: -2.0602

Max Act: 1.3906. Min Act: -0.0000

Data Index: 781071 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 2.0602. Min Range: -2.0602

Max Act: 1.4130. Min Act: -0.0000

Data Index: 608907 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 2.0602. Min Range: -2.0602

Max Act: 1.4564. Min Act: -0.0000

Data Index: 267496 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 2.0602. Min Range: -2.0602

Max Act: 1.4008. Min Act: -0.0000

Data Index: 1252834 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 2.0602. Min Range: -2.0602

Max Act: 1.4277. Min Act: -0.0000

Data Index: 982600 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 2.0602. Min Range: -2.0602

Max Act: 1.2545. Min Act: -0.0000

Data Index: 1273193 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 2.0602. Min Range: -2.0602

Max Act: 1.4035. Min Act: -0.0000

Data Index: 1235056 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 2.0602. Min Range: -2.0602

Max Act: 1.2653. Min Act: -0.0000

Data Index: 1258737 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 2.0602. Min Range: -2.0602

Max Act: 1.3364. Min Act: -0.0000

Data Index: 92452 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 2.0602. Min Range: -2.0602

Max Act: 1.2915. Min Act: -0.0001

Data Index: 1081313 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 2.0602. Min Range: -2.0602

Max Act: 1.2832. Min Act: -0.0000

Data Index: 1281637 (C4 (Web Text))

Max Activating Token Index: 421