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

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

Neuron 3779 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: 1.1303. Min Range: -1.1303

Max Act: 1.1303. Min Act: -0.0001

Data Index: 992819 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 1.1303. Min Range: -1.1303

Max Act: 1.0637. Min Act: -0.0001

Data Index: 311772 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8587. Min Act: -0.0001

Data Index: 668716 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9387. Min Act: -0.0001

Data Index: 723787 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8227. Min Act: -0.0001

Data Index: 775023 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9725. Min Act: -0.0001

Data Index: 7580 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9376. Min Act: -0.0001

Data Index: 858073 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9197. Min Act: -0.0001

Data Index: 781572 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9571. Min Act: -0.0001

Data Index: 830196 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8931. Min Act: -0.0001

Data Index: 562273 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9042. Min Act: -0.0001

Data Index: 186339 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8874. Min Act: -0.0001

Data Index: 748899 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8345. Min Act: -0.0001

Data Index: 717699 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.7757. Min Act: -0.0001

Data Index: 13605 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.7952. Min Act: -0.0001

Data Index: 815330 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8187. Min Act: -0.0001

Data Index: 1095379 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.7908. Min Act: -0.0001

Data Index: 1308997 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.7830. Min Act: -0.0001

Data Index: 223701 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8384. Min Act: -0.0001

Data Index: 108767 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8001. Min Act: -0.0001

Data Index: 1519326 (Python Code)

Max Activating Token Index: 776