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

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

Neuron 26 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4526. Min Range: -3.4526

Max Act: 3.4526. Min Act: -0.0001

Data Index: 465853 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 3.4526. Min Range: -3.4526

Max Act: 3.0459. Min Act: -0.0001

Data Index: 1266396 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 3.4526. Min Range: -3.4526

Max Act: 3.0406. Min Act: -0.0001

Data Index: 744641 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 3.4526. Min Range: -3.4526

Max Act: 2.8446. Min Act: -0.0001

Data Index: 71535 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 3.4526. Min Range: -3.4526

Max Act: 2.8354. Min Act: -0.0001

Data Index: 602411 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 3.4526. Min Range: -3.4526

Max Act: 3.0121. Min Act: -0.0001

Data Index: 730947 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 3.4526. Min Range: -3.4526

Max Act: 2.7470. Min Act: -0.0001

Data Index: 779787 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 3.4526. Min Range: -3.4526

Max Act: 2.5804. Min Act: -0.0001

Data Index: 512551 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 3.4526. Min Range: -3.4526

Max Act: 2.5561. Min Act: -0.0001

Data Index: 111208 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 3.4526. Min Range: -3.4526

Max Act: 2.6898. Min Act: -0.0001

Data Index: 639970 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 3.4526. Min Range: -3.4526

Max Act: 2.5002. Min Act: -0.0001

Data Index: 640084 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 3.4526. Min Range: -3.4526

Max Act: 2.7938. Min Act: -0.0001

Data Index: 22682 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 3.4526. Min Range: -3.4526

Max Act: 2.4934. Min Act: -0.0001

Data Index: 320043 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 3.4526. Min Range: -3.4526

Max Act: 2.4638. Min Act: -0.0001

Data Index: 172831 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 3.4526. Min Range: -3.4526

Max Act: 2.1843. Min Act: -0.0001

Data Index: 1168454 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 3.4526. Min Range: -3.4526

Max Act: 2.5407. Min Act: -0.0001

Data Index: 102576 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 3.4526. Min Range: -3.4526

Max Act: 2.2609. Min Act: -0.0001

Data Index: 1020690 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 3.4526. Min Range: -3.4526

Max Act: 2.9070. Min Act: -0.0001

Data Index: 727134 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 3.4526. Min Range: -3.4526

Max Act: 2.2482. Min Act: -0.0001

Data Index: 81096 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 3.4526. Min Range: -3.4526

Max Act: 2.5764. Min Act: -0.0001

Data Index: 763822 (C4 (Web Text))

Max Activating Token Index: 618