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

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

Neuron 3745 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6499. Min Range: -2.6499

Max Act: 2.6499. Min Act: -0.0000

Data Index: 1446778 (Python Code)

Max Activating Token Index: 782

Text #1

Max Range: 2.6499. Min Range: -2.6499

Max Act: 2.6398. Min Act: -0.0000

Data Index: 1410361 (Python Code)

Max Activating Token Index: 579

Text #2

Max Range: 2.6499. Min Range: -2.6499

Max Act: 2.4971. Min Act: -0.0000

Data Index: 1635269 (Python Code)

Max Activating Token Index: 905

Text #3

Max Range: 2.6499. Min Range: -2.6499

Max Act: 2.5548. Min Act: -0.0000

Data Index: 1551209 (Python Code)

Max Activating Token Index: 931

Text #4

Max Range: 2.6499. Min Range: -2.6499

Max Act: 2.2768. Min Act: -0.0000

Data Index: 1643940 (Python Code)

Max Activating Token Index: 526

Text #5

Max Range: 2.6499. Min Range: -2.6499

Max Act: 2.1289. Min Act: -0.0000

Data Index: 1607782 (Python Code)

Max Activating Token Index: 91

Text #6

Max Range: 2.6499. Min Range: -2.6499

Max Act: 2.2288. Min Act: -0.0000

Data Index: 1420781 (Python Code)

Max Activating Token Index: 492

Text #7

Max Range: 2.6499. Min Range: -2.6499

Max Act: 2.1780. Min Act: -0.0000

Data Index: 1541779 (Python Code)

Max Activating Token Index: 29

Text #8

Max Range: 2.6499. Min Range: -2.6499

Max Act: 2.0396. Min Act: -0.0000

Data Index: 1363335 (Python Code)

Max Activating Token Index: 814

Text #9

Max Range: 2.6499. Min Range: -2.6499

Max Act: 1.9143. Min Act: -0.0000

Data Index: 1566900 (Python Code)

Max Activating Token Index: 218

Text #10

Max Range: 2.6499. Min Range: -2.6499

Max Act: 1.8299. Min Act: -0.0000

Data Index: 1552341 (Python Code)

Max Activating Token Index: 804

Text #11

Max Range: 2.6499. Min Range: -2.6499

Max Act: 2.0013. Min Act: -0.0000

Data Index: 1547498 (Python Code)

Max Activating Token Index: 247

Text #12

Max Range: 2.6499. Min Range: -2.6499

Max Act: 1.8911. Min Act: -0.0000

Data Index: 1466330 (Python Code)

Max Activating Token Index: 653

Text #13

Max Range: 2.6499. Min Range: -2.6499

Max Act: 1.9901. Min Act: -0.0000

Data Index: 1633153 (Python Code)

Max Activating Token Index: 202

Text #14

Max Range: 2.6499. Min Range: -2.6499

Max Act: 1.8772. Min Act: -0.0000

Data Index: 1562382 (Python Code)

Max Activating Token Index: 163

Text #15

Max Range: 2.6499. Min Range: -2.6499

Max Act: 1.8739. Min Act: -0.0000

Data Index: 1412490 (Python Code)

Max Activating Token Index: 535

Text #16

Max Range: 2.6499. Min Range: -2.6499

Max Act: 1.9885. Min Act: -0.0000

Data Index: 1453839 (Python Code)

Max Activating Token Index: 460

Text #17

Max Range: 2.6499. Min Range: -2.6499

Max Act: 1.8556. Min Act: -0.0000

Data Index: 1472634 (Python Code)

Max Activating Token Index: 1021

Text #18

Max Range: 2.6499. Min Range: -2.6499

Max Act: 2.0450. Min Act: -0.0000

Data Index: 1513807 (Python Code)

Max Activating Token Index: 752

Text #19

Max Range: 2.6499. Min Range: -2.6499

Max Act: 1.9010. Min Act: -0.0000

Data Index: 1579637 (Python Code)

Max Activating Token Index: 226