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

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

Neuron 1404 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: 0.3001. Min Range: -0.3001

Max Act: 0.3001. Min Act: -0.0000

Data Index: 730854 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 0.3001. Min Range: -0.3001

Max Act: 0.2865. Min Act: -0.0001

Data Index: 946184 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.3001. Min Range: -0.3001

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1332543 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.3001. Min Range: -0.3001

Max Act: 0.2718. Min Act: -0.0001

Data Index: 815483 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.3001. Min Range: -0.3001

Max Act: 0.2511. Min Act: -0.0000

Data Index: 357467 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.3001. Min Range: -0.3001

Max Act: 0.2519. Min Act: -0.0000

Data Index: 859971 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.3001. Min Range: -0.3001

Max Act: 0.2671. Min Act: -0.0001

Data Index: 1460663 (Python Code)

Max Activating Token Index: 849

Text #7

Max Range: 0.3001. Min Range: -0.3001

Max Act: 0.2477. Min Act: -0.0000

Data Index: 828627 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.3001. Min Range: -0.3001

Max Act: 0.2396. Min Act: -0.0000

Data Index: 639073 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 0.3001. Min Range: -0.3001

Max Act: 0.2479. Min Act: -0.0000

Data Index: 507652 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.3001. Min Range: -0.3001

Max Act: 0.2377. Min Act: -0.0000

Data Index: 833247 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.3001. Min Range: -0.3001

Max Act: 0.2437. Min Act: -0.0000

Data Index: 575813 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.3001. Min Range: -0.3001

Max Act: 0.2437. Min Act: -0.0001

Data Index: 347938 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.3001. Min Range: -0.3001

Max Act: 0.2481. Min Act: -0.0001

Data Index: 1569788 (Python Code)

Max Activating Token Index: 355

Text #14

Max Range: 0.3001. Min Range: -0.3001

Max Act: 0.2381. Min Act: -0.0000

Data Index: 748826 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.3001. Min Range: -0.3001

Max Act: 0.2297. Min Act: -0.0000

Data Index: 83094 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 0.3001. Min Range: -0.3001

Max Act: 0.2370. Min Act: -0.0000

Data Index: 418325 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.3001. Min Range: -0.3001

Max Act: 0.2330. Min Act: -0.0000

Data Index: 304584 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 0.3001. Min Range: -0.3001

Max Act: 0.2154. Min Act: -0.0000

Data Index: 102075 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.3001. Min Range: -0.3001

Max Act: 0.2238. Min Act: -0.0001

Data Index: 739171 (C4 (Web Text))

Max Activating Token Index: 526