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

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

Neuron 391 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4666. Min Range: -4.4666

Max Act: 4.4666. Min Act: -0.0000

Data Index: 1351066 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 4.4666. Min Range: -4.4666

Max Act: 4.4473. Min Act: -0.0000

Data Index: 1082425 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 4.4666. Min Range: -4.4666

Max Act: 3.6897. Min Act: -0.0000

Data Index: 116525 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 4.4666. Min Range: -4.4666

Max Act: 3.8722. Min Act: -0.0000

Data Index: 77015 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 4.4666. Min Range: -4.4666

Max Act: 3.6401. Min Act: -0.0000

Data Index: 301260 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 4.4666. Min Range: -4.4666

Max Act: 3.6094. Min Act: -0.0000

Data Index: 35684 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 4.4666. Min Range: -4.4666

Max Act: 3.5660. Min Act: -0.0000

Data Index: 482654 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 4.4666. Min Range: -4.4666

Max Act: 3.2148. Min Act: -0.0000

Data Index: 666875 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 4.4666. Min Range: -4.4666

Max Act: 3.2574. Min Act: -0.0000

Data Index: 785797 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 4.4666. Min Range: -4.4666

Max Act: 3.3808. Min Act: -0.0000

Data Index: 1545101 (Python Code)

Max Activating Token Index: 944

Text #10

Max Range: 4.4666. Min Range: -4.4666

Max Act: 3.1702. Min Act: -0.0000

Data Index: 1245490 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 4.4666. Min Range: -4.4666

Max Act: 3.1513. Min Act: 0.0000

Data Index: 1256990 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 4.4666. Min Range: -4.4666

Max Act: 3.2731. Min Act: -0.0000

Data Index: 113323 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 4.4666. Min Range: -4.4666

Max Act: 2.9797. Min Act: 0.0000

Data Index: 1534239 (Python Code)

Max Activating Token Index: 296

Text #14

Max Range: 4.4666. Min Range: -4.4666

Max Act: 3.0246. Min Act: -0.0000

Data Index: 931452 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 4.4666. Min Range: -4.4666

Max Act: 3.0046. Min Act: -0.0000

Data Index: 380978 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 4.4666. Min Range: -4.4666

Max Act: 2.6343. Min Act: -0.0000

Data Index: 1048276 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 4.4666. Min Range: -4.4666

Max Act: 2.6778. Min Act: -0.0000

Data Index: 179825 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 4.4666. Min Range: -4.4666

Max Act: 2.9582. Min Act: -0.0000

Data Index: 734973 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 4.4666. Min Range: -4.4666

Max Act: 2.6578. Min Act: -0.0000

Data Index: 327667 (C4 (Web Text))

Max Activating Token Index: 144