Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3490 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0822. Min Act: -0.0001

Data Index: 971296 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1005595 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0687. Min Act: -0.0001

Data Index: 1429978 (Python Code)

Max Activating Token Index: 1015

Text #3

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0576. Min Act: -0.0001

Data Index: 309534 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1371568 (Python Code)

Max Activating Token Index: 767

Text #5

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0572. Min Act: -0.0002

Data Index: 983831 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0565. Min Act: -0.0001

Data Index: 1354153 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0559. Min Act: -0.0001

Data Index: 292920 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0576. Min Act: -0.0001

Data Index: 1472773 (Python Code)

Max Activating Token Index: 1002

Text #9

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0554. Min Act: -0.0002

Data Index: 915704 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0549. Min Act: -0.0002

Data Index: 836378 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0510. Min Act: -0.0001

Data Index: 1432531 (Python Code)

Max Activating Token Index: 815

Text #12

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0488. Min Act: -0.0001

Data Index: 467742 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0563. Min Act: -0.0001

Data Index: 1592632 (Python Code)

Max Activating Token Index: 313

Text #14

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0515. Min Act: -0.0001

Data Index: 568128 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0512. Min Act: -0.0002

Data Index: 203609 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0540. Min Act: -0.0001

Data Index: 171206 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1171733 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0512. Min Act: -0.0001

Data Index: 1292946 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0506. Min Act: -0.0001

Data Index: 372762 (C4 (Web Text))

Max Activating Token Index: 97