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

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

Neuron 1523 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6646. Min Range: -1.6646

Max Act: 1.6646. Min Act: -0.0001

Data Index: 722566 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 1.6646. Min Range: -1.6646

Max Act: 0.8198. Min Act: -0.0000

Data Index: 1049605 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 1.6646. Min Range: -1.6646

Max Act: 0.8031. Min Act: -0.0001

Data Index: 45548 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 1.6646. Min Range: -1.6646

Max Act: 0.8601. Min Act: -0.0001

Data Index: 340567 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 1.6646. Min Range: -1.6646

Max Act: 0.7663. Min Act: -0.0000

Data Index: 414052 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 1.6646. Min Range: -1.6646

Max Act: 0.7342. Min Act: -0.0001

Data Index: 910529 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 1.6646. Min Range: -1.6646

Max Act: 0.7330. Min Act: -0.0001

Data Index: 393251 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 1.6646. Min Range: -1.6646

Max Act: 0.6179. Min Act: -0.0000

Data Index: 256008 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 1.6646. Min Range: -1.6646

Max Act: 0.6587. Min Act: -0.0000

Data Index: 191837 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 1.6646. Min Range: -1.6646

Max Act: 0.6804. Min Act: -0.0000

Data Index: 699481 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 1.6646. Min Range: -1.6646

Max Act: 0.6975. Min Act: -0.0001

Data Index: 867036 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 1.6646. Min Range: -1.6646

Max Act: 0.7096. Min Act: -0.0000

Data Index: 261886 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 1.6646. Min Range: -1.6646

Max Act: 0.6218. Min Act: -0.0000

Data Index: 190903 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 1.6646. Min Range: -1.6646

Max Act: 0.6392. Min Act: -0.0000

Data Index: 657583 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 1.6646. Min Range: -1.6646

Max Act: 0.6044. Min Act: -0.0000

Data Index: 279328 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 1.6646. Min Range: -1.6646

Max Act: 0.6506. Min Act: -0.0001

Data Index: 751614 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 1.6646. Min Range: -1.6646

Max Act: 0.6654. Min Act: -0.0001

Data Index: 293881 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 1.6646. Min Range: -1.6646

Max Act: 0.6581. Min Act: -0.0000

Data Index: 812353 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 1.6646. Min Range: -1.6646

Max Act: 0.5651. Min Act: -0.0001

Data Index: 200326 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 1.6646. Min Range: -1.6646

Max Act: 0.6144. Min Act: -0.0000

Data Index: 483048 (C4 (Web Text))

Max Activating Token Index: 572