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

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

Neuron 4626 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8672. Min Range: -0.8672

Max Act: 0.8672. Min Act: -0.0001

Data Index: 1148666 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 0.8672. Min Range: -0.8672

Max Act: 0.7059. Min Act: -0.0001

Data Index: 901141 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 0.8672. Min Range: -0.8672

Max Act: 0.7624. Min Act: -0.0000

Data Index: 947775 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.8672. Min Range: -0.8672

Max Act: 0.7781. Min Act: -0.0001

Data Index: 1030959 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.8672. Min Range: -0.8672

Max Act: 0.6841. Min Act: -0.0001

Data Index: 867415 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 0.8672. Min Range: -0.8672

Max Act: 0.6863. Min Act: -0.0001

Data Index: 443271 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 0.8672. Min Range: -0.8672

Max Act: 0.6237. Min Act: -0.0001

Data Index: 1122121 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.8672. Min Range: -0.8672

Max Act: 0.5871. Min Act: -0.0000

Data Index: 1165465 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.8672. Min Range: -0.8672

Max Act: 0.5706. Min Act: -0.0000

Data Index: 788609 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.8672. Min Range: -0.8672

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1140784 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.8672. Min Range: -0.8672

Max Act: 0.5369. Min Act: -0.0001

Data Index: 946549 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.8672. Min Range: -0.8672

Max Act: 0.5151. Min Act: -0.0000

Data Index: 887270 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.8672. Min Range: -0.8672

Max Act: 0.5428. Min Act: -0.0001

Data Index: 126999 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.8672. Min Range: -0.8672

Max Act: 0.5380. Min Act: -0.0001

Data Index: 1049246 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.8672. Min Range: -0.8672

Max Act: 0.5118. Min Act: -0.0001

Data Index: 591603 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.8672. Min Range: -0.8672

Max Act: 0.4707. Min Act: -0.0001

Data Index: 1067934 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.8672. Min Range: -0.8672

Max Act: 0.4827. Min Act: -0.0001

Data Index: 639230 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.8672. Min Range: -0.8672

Max Act: 0.4681. Min Act: -0.0001

Data Index: 1061464 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.8672. Min Range: -0.8672

Max Act: 0.4606. Min Act: -0.0001

Data Index: 1303652 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.8672. Min Range: -0.8672

Max Act: 0.4488. Min Act: -0.0001

Data Index: 1342143 (C4 (Web Text))

Max Activating Token Index: 507