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

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

Neuron 2335 in Layer 1

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: 0.0676. Min Range: -0.0676

Max Act: 0.0671. Min Act: -0.0002

Data Index: 1087768 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0676. Min Act: -0.0002

Data Index: 350728 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0640. Min Act: -0.0002

Data Index: 898991 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0627. Min Act: -0.0002

Data Index: 429031 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0615. Min Act: -0.0002

Data Index: 698200 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0619. Min Act: -0.0002

Data Index: 397789 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0614. Min Act: -0.0002

Data Index: 822290 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0614. Min Act: -0.0002

Data Index: 986600 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0585. Min Act: -0.0003

Data Index: 621873 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0590. Min Act: -0.0002

Data Index: 170838 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0568. Min Act: -0.0002

Data Index: 740664 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0562. Min Act: -0.0002

Data Index: 543759 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0547. Min Act: -0.0002

Data Index: 516175 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0550. Min Act: -0.0002

Data Index: 292348 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0547. Min Act: -0.0002

Data Index: 944626 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0553. Min Act: -0.0002

Data Index: 955410 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0552. Min Act: -0.0003

Data Index: 723612 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0550. Min Act: -0.0002

Data Index: 928323 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0549. Min Act: -0.0002

Data Index: 114929 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0543. Min Act: -0.0002

Data Index: 48540 (C4 (Web Text))

Max Activating Token Index: 857