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

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

Neuron 1270 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: 0.3099. Min Range: -0.3099

Max Act: 0.3099. Min Act: -0.0001

Data Index: 30606 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.3023. Min Act: -0.0000

Data Index: 1434252 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2788. Min Act: -0.0001

Data Index: 205889 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2857. Min Act: -0.0001

Data Index: 1179337 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2835. Min Act: -0.0001

Data Index: 1305336 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2620. Min Act: -0.0000

Data Index: 1453583 (Python Code)

Max Activating Token Index: 732

Text #6

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2798. Min Act: -0.0001

Data Index: 156354 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2793. Min Act: -0.0001

Data Index: 444042 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2788. Min Act: -0.0001

Data Index: 1206236 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2681. Min Act: -0.0001

Data Index: 23120 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2779. Min Act: -0.0001

Data Index: 468251 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2827. Min Act: -0.0000

Data Index: 1656024 (Python Code)

Max Activating Token Index: 718

Text #12

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2758. Min Act: -0.0001

Data Index: 121264 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2747. Min Act: -0.0001

Data Index: 1079503 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2722. Min Act: -0.0001

Data Index: 396971 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2633. Min Act: -0.0001

Data Index: 572863 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2682. Min Act: -0.0001

Data Index: 1307600 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2659. Min Act: -0.0001

Data Index: 752791 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2558. Min Act: -0.0001

Data Index: 151326 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2738. Min Act: -0.0001

Data Index: 927087 (C4 (Web Text))

Max Activating Token Index: 448