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

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

Neuron 4607 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: 2.0980. Min Range: -2.0980

Max Act: 2.0980. Min Act: -0.0000

Data Index: 1007929 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 2.0980. Min Range: -2.0980

Max Act: 2.0648. Min Act: -0.0000

Data Index: 49840 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 2.0980. Min Range: -2.0980

Max Act: 2.0755. Min Act: -0.0000

Data Index: 542055 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 2.0980. Min Range: -2.0980

Max Act: 1.7197. Min Act: -0.0000

Data Index: 615776 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 2.0980. Min Range: -2.0980

Max Act: 1.5524. Min Act: -0.0000

Data Index: 681043 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 2.0980. Min Range: -2.0980

Max Act: 1.8227. Min Act: -0.0000

Data Index: 506156 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 2.0980. Min Range: -2.0980

Max Act: 1.4648. Min Act: -0.0000

Data Index: 385848 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 2.0980. Min Range: -2.0980

Max Act: 1.5137. Min Act: -0.0000

Data Index: 1185020 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 2.0980. Min Range: -2.0980

Max Act: 1.4175. Min Act: -0.0000

Data Index: 237587 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 2.0980. Min Range: -2.0980

Max Act: 1.4631. Min Act: -0.0000

Data Index: 1075254 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 2.0980. Min Range: -2.0980

Max Act: 1.5490. Min Act: -0.0000

Data Index: 838507 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 2.0980. Min Range: -2.0980

Max Act: 1.4441. Min Act: -0.0000

Data Index: 471654 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 2.0980. Min Range: -2.0980

Max Act: 1.3520. Min Act: -0.0001

Data Index: 886756 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 2.0980. Min Range: -2.0980

Max Act: 1.3547. Min Act: -0.0000

Data Index: 285889 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 2.0980. Min Range: -2.0980

Max Act: 1.4056. Min Act: -0.0000

Data Index: 1241900 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 2.0980. Min Range: -2.0980

Max Act: 1.4887. Min Act: -0.0000

Data Index: 928641 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 2.0980. Min Range: -2.0980

Max Act: 1.3697. Min Act: -0.0000

Data Index: 1296619 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 2.0980. Min Range: -2.0980

Max Act: 1.3039. Min Act: -0.0000

Data Index: 339827 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 2.0980. Min Range: -2.0980

Max Act: 1.3688. Min Act: -0.0000

Data Index: 1281795 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 2.0980. Min Range: -2.0980

Max Act: 1.2985. Min Act: -0.0000

Data Index: 932848 (C4 (Web Text))

Max Activating Token Index: 887