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

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

Neuron 3911 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0708. Min Act: -0.0001

Data Index: 709720 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0653. Min Act: -0.0001

Data Index: 915347 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0697. Min Act: -0.0001

Data Index: 823409 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0657. Min Act: -0.0001

Data Index: 444112 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0740. Min Act: -0.0001

Data Index: 640299 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0639. Min Act: -0.0001

Data Index: 1500511 (Python Code)

Max Activating Token Index: 476

Text #6

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0630. Min Act: -0.0001

Data Index: 1622114 (Python Code)

Max Activating Token Index: 316

Text #7

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0618. Min Act: -0.0001

Data Index: 627181 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0606. Min Act: -0.0001

Data Index: 1433290 (Python Code)

Max Activating Token Index: 460

Text #9

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0629. Min Act: -0.0001

Data Index: 697791 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0553. Min Act: -0.0001

Data Index: 1582271 (Python Code)

Max Activating Token Index: 304

Text #11

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0565. Min Act: -0.0001

Data Index: 544431 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0649. Min Act: -0.0001

Data Index: 1479142 (Python Code)

Max Activating Token Index: 359

Text #13

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1649566 (Python Code)

Max Activating Token Index: 443

Text #14

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0562. Min Act: -0.0001

Data Index: 1020823 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0558. Min Act: -0.0001

Data Index: 1077446 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0596. Min Act: -0.0001

Data Index: 883141 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0583. Min Act: -0.0001

Data Index: 116860 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0607. Min Act: -0.0001

Data Index: 694295 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0569. Min Act: -0.0001

Data Index: 288462 (C4 (Web Text))

Max Activating Token Index: 524