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

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

Neuron 3165 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0304. Min Range: -1.0304

Max Act: 1.0304. Min Act: -0.0001

Data Index: 1576490 (Python Code)

Max Activating Token Index: 643

Text #1

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.9651. Min Act: -0.0001

Data Index: 1582532 (Python Code)

Max Activating Token Index: 689

Text #2

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.8716. Min Act: -0.0001

Data Index: 1413167 (Python Code)

Max Activating Token Index: 218

Text #3

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.8103. Min Act: -0.0001

Data Index: 1376707 (Python Code)

Max Activating Token Index: 370

Text #4

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.8287. Min Act: -0.0001

Data Index: 1646708 (Python Code)

Max Activating Token Index: 893

Text #5

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.8211. Min Act: -0.0001

Data Index: 1504126 (Python Code)

Max Activating Token Index: 833

Text #6

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.8202. Min Act: -0.0001

Data Index: 1656220 (Python Code)

Max Activating Token Index: 56

Text #7

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.7549. Min Act: -0.0001

Data Index: 1397075 (Python Code)

Max Activating Token Index: 880

Text #8

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.8619. Min Act: -0.0001

Data Index: 1633111 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.8398. Min Act: -0.0001

Data Index: 1414684 (Python Code)

Max Activating Token Index: 616

Text #10

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.8498. Min Act: -0.0001

Data Index: 1442823 (Python Code)

Max Activating Token Index: 898

Text #11

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.7905. Min Act: -0.0001

Data Index: 645693 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.7622. Min Act: -0.0001

Data Index: 1386269 (Python Code)

Max Activating Token Index: 50

Text #13

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.8007. Min Act: -0.0001

Data Index: 543646 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.7743. Min Act: -0.0001

Data Index: 69495 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.7000. Min Act: -0.0001

Data Index: 961412 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.7731. Min Act: -0.0001

Data Index: 181674 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.7417. Min Act: -0.0001

Data Index: 1546850 (Python Code)

Max Activating Token Index: 685

Text #18

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.7612. Min Act: -0.0001

Data Index: 254581 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.7491. Min Act: -0.0001

Data Index: 797581 (C4 (Web Text))

Max Activating Token Index: 166