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

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

Neuron 2879 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: 0.8833. Min Range: -0.8833

Max Act: 0.8833. Min Act: -0.0001

Data Index: 1491896 (Python Code)

Max Activating Token Index: 181

Text #1

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8229. Min Act: -0.0001

Data Index: 1472248 (Python Code)

Max Activating Token Index: 748

Text #2

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8694. Min Act: -0.0001

Data Index: 1369308 (Python Code)

Max Activating Token Index: 509

Text #3

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.7879. Min Act: -0.0000

Data Index: 1646379 (Python Code)

Max Activating Token Index: 597

Text #4

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8101. Min Act: -0.0001

Data Index: 1604628 (Python Code)

Max Activating Token Index: 246

Text #5

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.8204. Min Act: -0.0000

Data Index: 1434364 (Python Code)

Max Activating Token Index: 56

Text #6

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.7837. Min Act: -0.0001

Data Index: 1589708 (Python Code)

Max Activating Token Index: 85

Text #7

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.7834. Min Act: -0.0000

Data Index: 1588360 (Python Code)

Max Activating Token Index: 166

Text #8

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.7671. Min Act: -0.0000

Data Index: 1435632 (Python Code)

Max Activating Token Index: 339

Text #9

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.7659. Min Act: -0.0000

Data Index: 1546465 (Python Code)

Max Activating Token Index: 477

Text #10

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.7660. Min Act: -0.0000

Data Index: 576916 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.6861. Min Act: -0.0000

Data Index: 561463 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1074691 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1237876 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.6876. Min Act: -0.0001

Data Index: 560939 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.7091. Min Act: -0.0001

Data Index: 268967 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.6593. Min Act: -0.0000

Data Index: 596255 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.6616. Min Act: -0.0000

Data Index: 1103604 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.6380. Min Act: -0.0000

Data Index: 1090810 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.8833. Min Range: -0.8833

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1577258 (Python Code)

Max Activating Token Index: 885