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

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

Neuron 1837 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.8604. Min Act: -0.0000

Data Index: 297132 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.5602. Min Act: -0.0000

Data Index: 832432 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4934. Min Act: -0.0000

Data Index: 264776 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.5012. Min Act: -0.0000

Data Index: 59315 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4708. Min Act: -0.0000

Data Index: 157311 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4642. Min Act: -0.0000

Data Index: 835180 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4645. Min Act: 0.0001

Data Index: 740146 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4950. Min Act: -0.0000

Data Index: 225782 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4578. Min Act: -0.0000

Data Index: 970595 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4617. Min Act: -0.0000

Data Index: 229850 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4389. Min Act: -0.0000

Data Index: 440015 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4597. Min Act: -0.0000

Data Index: 723307 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4542. Min Act: -0.0000

Data Index: 1022088 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4411. Min Act: -0.0000

Data Index: 481198 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4652. Min Act: -0.0000

Data Index: 1001399 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4693. Min Act: -0.0000

Data Index: 24534 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4440. Min Act: -0.0000

Data Index: 143637 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1322170 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4321. Min Act: -0.0000

Data Index: 903606 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4330. Min Act: -0.0000

Data Index: 71482 (C4 (Web Text))

Max Activating Token Index: 108