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

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

Neuron 3236 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1487. Min Range: -2.1487

Max Act: 2.1487. Min Act: -0.0000

Data Index: 1461718 (Python Code)

Max Activating Token Index: 136

Text #1

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.4192. Min Act: -0.0000

Data Index: 1577301 (Python Code)

Max Activating Token Index: 844

Text #2

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.4491. Min Act: -0.0000

Data Index: 1530114 (Python Code)

Max Activating Token Index: 446

Text #3

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.3750. Min Act: -0.0000

Data Index: 1500886 (Python Code)

Max Activating Token Index: 743

Text #4

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.3587. Min Act: -0.0000

Data Index: 1494901 (Python Code)

Max Activating Token Index: 933

Text #5

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.4233. Min Act: -0.0000

Data Index: 1651736 (Python Code)

Max Activating Token Index: 854

Text #6

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.0934. Min Act: -0.0000

Data Index: 1578881 (Python Code)

Max Activating Token Index: 453

Text #7

Max Range: 2.1487. Min Range: -2.1487

Max Act: 0.9871. Min Act: -0.0000

Data Index: 1425915 (Python Code)

Max Activating Token Index: 155

Text #8

Max Range: 2.1487. Min Range: -2.1487

Max Act: 0.8682. Min Act: -0.0000

Data Index: 1561629 (Python Code)

Max Activating Token Index: 428

Text #9

Max Range: 2.1487. Min Range: -2.1487

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1328475 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 2.1487. Min Range: -2.1487

Max Act: 0.6085. Min Act: -0.0000

Data Index: 281532 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 2.1487. Min Range: -2.1487

Max Act: 0.5902. Min Act: 0.0000

Data Index: 669872 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 2.1487. Min Range: -2.1487

Max Act: 0.5643. Min Act: 0.0000

Data Index: 1348559 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 2.1487. Min Range: -2.1487

Max Act: 0.5775. Min Act: 0.0000

Data Index: 180565 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 2.1487. Min Range: -2.1487

Max Act: 0.5452. Min Act: 0.0000

Data Index: 1086117 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 2.1487. Min Range: -2.1487

Max Act: 0.5270. Min Act: -0.0000

Data Index: 824654 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 2.1487. Min Range: -2.1487

Max Act: 0.4604. Min Act: -0.0000

Data Index: 908669 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 2.1487. Min Range: -2.1487

Max Act: 0.5135. Min Act: -0.0000

Data Index: 711435 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 2.1487. Min Range: -2.1487

Max Act: 0.5300. Min Act: -0.0000

Data Index: 109035 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 2.1487. Min Range: -2.1487

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1059830 (C4 (Web Text))

Max Activating Token Index: 144