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

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

Neuron 1936 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5638. Min Range: -1.5638

Max Act: 1.5638. Min Act: -0.0000

Data Index: 487753 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 1.5638. Min Range: -1.5638

Max Act: 1.5418. Min Act: -0.0000

Data Index: 250170 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 1.5638. Min Range: -1.5638

Max Act: 1.4250. Min Act: -0.0000

Data Index: 986381 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 1.5638. Min Range: -1.5638

Max Act: 1.4526. Min Act: -0.0000

Data Index: 158848 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 1.5638. Min Range: -1.5638

Max Act: 1.4098. Min Act: -0.0000

Data Index: 597204 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 1.5638. Min Range: -1.5638

Max Act: 1.4139. Min Act: -0.0000

Data Index: 899353 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 1.5638. Min Range: -1.5638

Max Act: 1.3906. Min Act: -0.0000

Data Index: 880172 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 1.5638. Min Range: -1.5638

Max Act: 1.3133. Min Act: -0.0000

Data Index: 1585084 (Python Code)

Max Activating Token Index: 510

Text #8

Max Range: 1.5638. Min Range: -1.5638

Max Act: 1.1932. Min Act: -0.0000

Data Index: 191903 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 1.5638. Min Range: -1.5638

Max Act: 1.2435. Min Act: -0.0000

Data Index: 353752 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 1.5638. Min Range: -1.5638

Max Act: 1.1732. Min Act: -0.0000

Data Index: 1041776 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 1.5638. Min Range: -1.5638

Max Act: 1.2089. Min Act: -0.0000

Data Index: 903606 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 1.5638. Min Range: -1.5638

Max Act: 1.1939. Min Act: -0.0000

Data Index: 1003325 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 1.5638. Min Range: -1.5638

Max Act: 1.1934. Min Act: -0.0000

Data Index: 233152 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 1.5638. Min Range: -1.5638

Max Act: 1.1873. Min Act: -0.0000

Data Index: 1237710 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 1.5638. Min Range: -1.5638

Max Act: 1.2546. Min Act: -0.0000

Data Index: 1541213 (Python Code)

Max Activating Token Index: 375

Text #16

Max Range: 1.5638. Min Range: -1.5638

Max Act: 1.1607. Min Act: -0.0000

Data Index: 1497542 (Python Code)

Max Activating Token Index: 895

Text #17

Max Range: 1.5638. Min Range: -1.5638

Max Act: 1.1710. Min Act: -0.0000

Data Index: 602009 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 1.5638. Min Range: -1.5638

Max Act: 1.1674. Min Act: -0.0000

Data Index: 493751 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 1.5638. Min Range: -1.5638

Max Act: 1.1567. Min Act: -0.0000

Data Index: 1112567 (C4 (Web Text))

Max Activating Token Index: 109