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

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

Neuron 26 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0869. Min Range: -3.0869

Max Act: 3.0869. Min Act: -0.0000

Data Index: 157560 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.5735. Min Act: -0.0000

Data Index: 132869 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.4197. Min Act: -0.0000

Data Index: 525774 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.6067. Min Act: -0.0000

Data Index: 47217 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.2294. Min Act: -0.0000

Data Index: 1229810 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.4060. Min Act: -0.0000

Data Index: 383642 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.2919. Min Act: -0.0000

Data Index: 1008681 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.1538. Min Act: -0.0000

Data Index: 702245 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.1485. Min Act: -0.0000

Data Index: 512234 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.2317. Min Act: -0.0000

Data Index: 1120171 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.2169. Min Act: -0.0000

Data Index: 1147109 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.0762. Min Act: -0.0000

Data Index: 888651 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.1621. Min Act: -0.0000

Data Index: 683366 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.1551. Min Act: -0.0000

Data Index: 1021257 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.1480. Min Act: -0.0000

Data Index: 389151 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.1298. Min Act: -0.0000

Data Index: 15555 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.1176. Min Act: -0.0000

Data Index: 448320 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.1056. Min Act: -0.0000

Data Index: 1192946 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 3.0869. Min Range: -3.0869

Max Act: 2.1111. Min Act: -0.0000

Data Index: 972649 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 3.0869. Min Range: -3.0869

Max Act: 1.9916. Min Act: -0.0000

Data Index: 301536 (C4 (Web Text))

Max Activating Token Index: 294