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

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

Neuron 1381 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0864. Min Act: -0.0002

Data Index: 1437604 (Python Code)

Max Activating Token Index: 854

Text #1

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0821. Min Act: -0.0002

Data Index: 986024 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0795. Min Act: -0.0002

Data Index: 1561187 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1407334 (Python Code)

Max Activating Token Index: 575

Text #4

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1516980 (Python Code)

Max Activating Token Index: 625

Text #5

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1373068 (Python Code)

Max Activating Token Index: 722

Text #6

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1316510 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0771. Min Act: -0.0002

Data Index: 754260 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1106074 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0742. Min Act: -0.0002

Data Index: 1283681 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0741. Min Act: -0.0002

Data Index: 330259 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0765. Min Act: -0.0002

Data Index: 1250996 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1414763 (Python Code)

Max Activating Token Index: 639

Text #13

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0726. Min Act: -0.0002

Data Index: 1492288 (Python Code)

Max Activating Token Index: 382

Text #14

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0731. Min Act: -0.0002

Data Index: 820894 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0723. Min Act: -0.0002

Data Index: 776307 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0713. Min Act: -0.0002

Data Index: 1604015 (Python Code)

Max Activating Token Index: 41

Text #17

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1522346 (Python Code)

Max Activating Token Index: 639

Text #18

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0726. Min Act: -0.0002

Data Index: 311288 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0666. Min Act: -0.0002

Data Index: 1609794 (Python Code)

Max Activating Token Index: 540