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

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

Neuron 2949 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5940. Min Act: -0.0001

Data Index: 1518541 (Python Code)

Max Activating Token Index: 782

Text #1

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4242. Min Act: -0.0001

Data Index: 1652022 (Python Code)

Max Activating Token Index: 960

Text #2

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4468. Min Act: -0.0001

Data Index: 1467556 (Python Code)

Max Activating Token Index: 490

Text #3

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4709. Min Act: -0.0001

Data Index: 1533699 (Python Code)

Max Activating Token Index: 148

Text #4

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4352. Min Act: -0.0001

Data Index: 1448353 (Python Code)

Max Activating Token Index: 57

Text #5

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1556201 (Python Code)

Max Activating Token Index: 166

Text #6

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4720. Min Act: -0.0001

Data Index: 1401990 (Python Code)

Max Activating Token Index: 469

Text #7

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4121. Min Act: -0.0000

Data Index: 1533384 (Python Code)

Max Activating Token Index: 42

Text #8

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4218. Min Act: -0.0001

Data Index: 1618148 (Python Code)

Max Activating Token Index: 495

Text #9

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1369099 (Python Code)

Max Activating Token Index: 221

Text #10

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4093. Min Act: -0.0001

Data Index: 1568013 (Python Code)

Max Activating Token Index: 78

Text #11

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4204. Min Act: -0.0001

Data Index: 1572086 (Python Code)

Max Activating Token Index: 409

Text #12

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3943. Min Act: -0.0000

Data Index: 1536845 (Python Code)

Max Activating Token Index: 95

Text #13

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3407. Min Act: -0.0000

Data Index: 1615339 (Python Code)

Max Activating Token Index: 715

Text #14

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3510. Min Act: -0.0000

Data Index: 1468688 (Python Code)

Max Activating Token Index: 150

Text #15

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3515. Min Act: -0.0000

Data Index: 1473077 (Python Code)

Max Activating Token Index: 27

Text #16

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3598. Min Act: -0.0000

Data Index: 1623944 (Python Code)

Max Activating Token Index: 662

Text #17

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3480. Min Act: -0.0001

Data Index: 1566949 (Python Code)

Max Activating Token Index: 694

Text #18

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3276. Min Act: -0.0001

Data Index: 1615675 (Python Code)

Max Activating Token Index: 877

Text #19

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3612. Min Act: -0.0000

Data Index: 1392353 (Python Code)

Max Activating Token Index: 156