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

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

Neuron 1518 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0724. Min Act: -0.0001

Data Index: 707132 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0691. Min Act: -0.0001

Data Index: 1043087 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0683. Min Act: -0.0001

Data Index: 57514 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0656. Min Act: -0.0001

Data Index: 671379 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0654. Min Act: -0.0001

Data Index: 1027972 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0662. Min Act: -0.0001

Data Index: 587916 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0654. Min Act: -0.0001

Data Index: 1500431 (Python Code)

Max Activating Token Index: 203

Text #7

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1271636 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0649. Min Act: -0.0001

Data Index: 594429 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0652. Min Act: -0.0001

Data Index: 969396 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0635. Min Act: -0.0001

Data Index: 445110 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0638. Min Act: -0.0001

Data Index: 527976 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0629. Min Act: -0.0001

Data Index: 508957 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0628. Min Act: -0.0002

Data Index: 40806 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0619. Min Act: -0.0001

Data Index: 1203304 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0637. Min Act: -0.0001

Data Index: 787098 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0618. Min Act: -0.0001

Data Index: 897572 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0623. Min Act: -0.0001

Data Index: 1583356 (Python Code)

Max Activating Token Index: 27

Text #18

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0627. Min Act: -0.0001

Data Index: 1019413 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0623. Min Act: -0.0001

Data Index: 1091072 (C4 (Web Text))

Max Activating Token Index: 787