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

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

Neuron 4520 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0734. Min Range: -3.0734

Max Act: 3.0734. Min Act: -0.0000

Data Index: 1523354 (Python Code)

Max Activating Token Index: 911

Text #1

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.8763. Min Act: -0.0000

Data Index: 1439385 (Python Code)

Max Activating Token Index: 212

Text #2

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.6771. Min Act: -0.0000

Data Index: 388770 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.7280. Min Act: -0.0000

Data Index: 1553947 (Python Code)

Max Activating Token Index: 734

Text #4

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.3182. Min Act: -0.0000

Data Index: 728743 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.2701. Min Act: -0.0000

Data Index: 1503955 (Python Code)

Max Activating Token Index: 19

Text #6

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.3430. Min Act: -0.0000

Data Index: 1042718 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.1928. Min Act: -0.0000

Data Index: 1020902 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.1822. Min Act: -0.0000

Data Index: 1138788 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.1839. Min Act: -0.0000

Data Index: 1216466 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.1741. Min Act: -0.0000

Data Index: 388618 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.2834. Min Act: -0.0000

Data Index: 577283 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.1245. Min Act: -0.0000

Data Index: 670916 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.0123. Min Act: -0.0000

Data Index: 1182022 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.2485. Min Act: -0.0000

Data Index: 947493 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.0947. Min Act: -0.0000

Data Index: 1443835 (Python Code)

Max Activating Token Index: 190

Text #16

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.1782. Min Act: -0.0000

Data Index: 908470 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.1834. Min Act: -0.0000

Data Index: 1063220 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.0467. Min Act: -0.0000

Data Index: 343365 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.1400. Min Act: -0.0000

Data Index: 664624 (C4 (Web Text))

Max Activating Token Index: 577