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

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

Neuron 1670 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: 0.7700. Min Range: -0.7700

Max Act: 0.7700. Min Act: -0.0002

Data Index: 1606575 (Python Code)

Max Activating Token Index: 345

Text #1

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.7543. Min Act: -0.0002

Data Index: 1527606 (Python Code)

Max Activating Token Index: 364

Text #2

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.7645. Min Act: -0.0002

Data Index: 1563903 (Python Code)

Max Activating Token Index: 742

Text #3

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.7490. Min Act: -0.0002

Data Index: 1627004 (Python Code)

Max Activating Token Index: 541

Text #4

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.7240. Min Act: -0.0002

Data Index: 1488157 (Python Code)

Max Activating Token Index: 255

Text #5

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.7432. Min Act: -0.0002

Data Index: 1386963 (Python Code)

Max Activating Token Index: 409

Text #6

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.7239. Min Act: -0.0002

Data Index: 1409318 (Python Code)

Max Activating Token Index: 617

Text #7

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.7357. Min Act: -0.0002

Data Index: 1578784 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.7133. Min Act: -0.0002

Data Index: 1506251 (Python Code)

Max Activating Token Index: 914

Text #9

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6917. Min Act: -0.0002

Data Index: 1397593 (Python Code)

Max Activating Token Index: 303

Text #10

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.7016. Min Act: -0.0002

Data Index: 1639587 (Python Code)

Max Activating Token Index: 204

Text #11

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6899. Min Act: -0.0002

Data Index: 1502573 (Python Code)

Max Activating Token Index: 625

Text #12

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6904. Min Act: -0.0002

Data Index: 1460266 (Python Code)

Max Activating Token Index: 904

Text #13

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6816. Min Act: -0.0002

Data Index: 1624993 (Python Code)

Max Activating Token Index: 757

Text #14

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6874. Min Act: -0.0002

Data Index: 1652046 (Python Code)

Max Activating Token Index: 929

Text #15

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6907. Min Act: -0.0002

Data Index: 1543420 (Python Code)

Max Activating Token Index: 203

Text #16

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6754. Min Act: -0.0002

Data Index: 1462165 (Python Code)

Max Activating Token Index: 188

Text #17

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6691. Min Act: -0.0002

Data Index: 1646855 (Python Code)

Max Activating Token Index: 270

Text #18

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6564. Min Act: -0.0002

Data Index: 1366680 (Python Code)

Max Activating Token Index: 979

Text #19

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6650. Min Act: -0.0002

Data Index: 1545907 (Python Code)

Max Activating Token Index: 1017