Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 930 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.4274. Min Act: -0.0001

Data Index: 1568389 (Python Code)

Max Activating Token Index: 610

Text #1

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3825. Min Act: -0.0000

Data Index: 686251 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3427. Min Act: -0.0001

Data Index: 1626460 (Python Code)

Max Activating Token Index: 422

Text #3

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2648. Min Act: -0.0001

Data Index: 1519207 (Python Code)

Max Activating Token Index: 809

Text #4

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3189. Min Act: -0.0000

Data Index: 438693 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3062. Min Act: -0.0001

Data Index: 1468082 (Python Code)

Max Activating Token Index: 1007

Text #6

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2969. Min Act: -0.0001

Data Index: 1543301 (Python Code)

Max Activating Token Index: 874

Text #7

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2954. Min Act: -0.0000

Data Index: 23665 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2733. Min Act: -0.0001

Data Index: 1589523 (Python Code)

Max Activating Token Index: 617

Text #9

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2674. Min Act: -0.0000

Data Index: 319160 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2552. Min Act: -0.0001

Data Index: 1598905 (Python Code)

Max Activating Token Index: 699

Text #11

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2555. Min Act: -0.0001

Data Index: 1572814 (Python Code)

Max Activating Token Index: 80

Text #12

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2626. Min Act: -0.0001

Data Index: 1583990 (Python Code)

Max Activating Token Index: 821

Text #13

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2512. Min Act: -0.0000

Data Index: 396997 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2751. Min Act: -0.0001

Data Index: 1409019 (Python Code)

Max Activating Token Index: 842

Text #15

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2928. Min Act: -0.0001

Data Index: 1537417 (Python Code)

Max Activating Token Index: 195

Text #16

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2537. Min Act: -0.0001

Data Index: 1517542 (Python Code)

Max Activating Token Index: 472

Text #17

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2324. Min Act: -0.0001

Data Index: 1613835 (Python Code)

Max Activating Token Index: 146

Text #18

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2326. Min Act: -0.0001

Data Index: 1486440 (Python Code)

Max Activating Token Index: 78

Text #19

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2300. Min Act: -0.0001

Data Index: 1420077 (Python Code)

Max Activating Token Index: 688