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

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

Neuron 4553 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: 0.0653. Min Range: -0.0653

Max Act: 0.0653. Min Act: -0.0001

Data Index: 1100689 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0641. Min Act: -0.0001

Data Index: 1375626 (Python Code)

Max Activating Token Index: 956

Text #2

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0642. Min Act: -0.0001

Data Index: 223006 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0616. Min Act: -0.0001

Data Index: 822438 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0615. Min Act: -0.0001

Data Index: 325112 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1095222 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0604. Min Act: -0.0001

Data Index: 651241 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0603. Min Act: -0.0001

Data Index: 33112 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0601. Min Act: -0.0001

Data Index: 706194 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0597. Min Act: -0.0001

Data Index: 1624713 (Python Code)

Max Activating Token Index: 139

Text #10

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1046004 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0596. Min Act: -0.0001

Data Index: 836875 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0588. Min Act: -0.0001

Data Index: 192663 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0588. Min Act: -0.0001

Data Index: 299634 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0584. Min Act: -0.0001

Data Index: 1577427 (Python Code)

Max Activating Token Index: 823

Text #15

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0582. Min Act: -0.0001

Data Index: 305195 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0585. Min Act: -0.0001

Data Index: 585799 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0577. Min Act: -0.0001

Data Index: 866716 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0580. Min Act: -0.0001

Data Index: 970980 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0586. Min Act: -0.0001

Data Index: 173864 (C4 (Web Text))

Max Activating Token Index: 414