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

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

Neuron 5677 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: 0.3409. Min Range: -0.3409

Max Act: 0.3409. Min Act: -0.0001

Data Index: 256193 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2891. Min Act: -0.0001

Data Index: 936318 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2900. Min Act: -0.0001

Data Index: 149997 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2803. Min Act: -0.0001

Data Index: 1192641 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2742. Min Act: -0.0001

Data Index: 743200 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2724. Min Act: -0.0001

Data Index: 889998 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2777. Min Act: -0.0001

Data Index: 871066 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2677. Min Act: -0.0001

Data Index: 720896 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2698. Min Act: -0.0001

Data Index: 907814 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2700. Min Act: -0.0001

Data Index: 663347 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2618. Min Act: -0.0001

Data Index: 1346242 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2640. Min Act: -0.0001

Data Index: 1345890 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2648. Min Act: -0.0001

Data Index: 880360 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2584. Min Act: -0.0001

Data Index: 1119886 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2516. Min Act: -0.0001

Data Index: 78641 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2538. Min Act: -0.0001

Data Index: 1100037 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2568. Min Act: -0.0001

Data Index: 1348818 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2531. Min Act: -0.0001

Data Index: 457556 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2469. Min Act: -0.0001

Data Index: 386294 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.3409. Min Range: -0.3409

Max Act: 0.2533. Min Act: -0.0001

Data Index: 1303042 (C4 (Web Text))

Max Activating Token Index: 1023