Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3496 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3551. Min Range: -1.3551

Max Act: 1.3551. Min Act: -0.0001

Data Index: 694969 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 1.3551. Min Range: -1.3551

Max Act: 1.2754. Min Act: -0.0000

Data Index: 252433 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 1.3551. Min Range: -1.3551

Max Act: 1.2655. Min Act: -0.0000

Data Index: 1124118 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 1.3551. Min Range: -1.3551

Max Act: 1.2751. Min Act: -0.0000

Data Index: 992419 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 1.3551. Min Range: -1.3551

Max Act: 1.2658. Min Act: -0.0000

Data Index: 698862 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 1.3551. Min Range: -1.3551

Max Act: 1.3018. Min Act: -0.0000

Data Index: 1086426 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 1.3551. Min Range: -1.3551

Max Act: 1.1418. Min Act: -0.0000

Data Index: 204809 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 1.3551. Min Range: -1.3551

Max Act: 1.2660. Min Act: -0.0000

Data Index: 649462 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 1.3551. Min Range: -1.3551

Max Act: 1.1573. Min Act: -0.0000

Data Index: 1045274 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 1.3551. Min Range: -1.3551

Max Act: 1.1975. Min Act: -0.0000

Data Index: 419222 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 1.3551. Min Range: -1.3551

Max Act: 1.0590. Min Act: -0.0000

Data Index: 408472 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 1.3551. Min Range: -1.3551

Max Act: 1.1339. Min Act: -0.0000

Data Index: 1239935 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 1.3551. Min Range: -1.3551

Max Act: 1.1698. Min Act: -0.0000

Data Index: 1173732 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 1.3551. Min Range: -1.3551

Max Act: 1.1398. Min Act: -0.0000

Data Index: 1295679 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 1.3551. Min Range: -1.3551

Max Act: 1.0966. Min Act: -0.0000

Data Index: 478833 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 1.3551. Min Range: -1.3551

Max Act: 1.1626. Min Act: -0.0000

Data Index: 982144 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 1.3551. Min Range: -1.3551

Max Act: 1.0365. Min Act: -0.0000

Data Index: 1242596 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 1.3551. Min Range: -1.3551

Max Act: 1.0907. Min Act: -0.0000

Data Index: 62300 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 1.3551. Min Range: -1.3551

Max Act: 1.0224. Min Act: -0.0000

Data Index: 879971 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 1.3551. Min Range: -1.3551

Max Act: 1.0367. Min Act: -0.0000

Data Index: 1123204 (C4 (Web Text))

Max Activating Token Index: 328