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

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

Neuron 651 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.5054. Min Act: 0.0000

Data Index: 1495413 (Python Code)

Max Activating Token Index: 493

Text #1

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4645. Min Act: 0.0000

Data Index: 1628113 (Python Code)

Max Activating Token Index: 118

Text #2

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1553065 (Python Code)

Max Activating Token Index: 100

Text #3

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1398091 (Python Code)

Max Activating Token Index: 163

Text #4

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3991. Min Act: -0.0000

Data Index: 1573218 (Python Code)

Max Activating Token Index: 433

Text #5

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1483919 (Python Code)

Max Activating Token Index: 289

Text #6

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1547433 (Python Code)

Max Activating Token Index: 848

Text #7

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4071. Min Act: -0.0000

Data Index: 1639137 (Python Code)

Max Activating Token Index: 565

Text #8

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3864. Min Act: -0.0000

Data Index: 1434340 (Python Code)

Max Activating Token Index: 716

Text #9

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3943. Min Act: -0.0000

Data Index: 1593828 (Python Code)

Max Activating Token Index: 370

Text #10

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1495484 (Python Code)

Max Activating Token Index: 381

Text #11

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3864. Min Act: -0.0000

Data Index: 1476428 (Python Code)

Max Activating Token Index: 338

Text #12

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1584934 (Python Code)

Max Activating Token Index: 342

Text #13

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3684. Min Act: -0.0000

Data Index: 1618084 (Python Code)

Max Activating Token Index: 130

Text #14

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3801. Min Act: -0.0000

Data Index: 1431406 (Python Code)

Max Activating Token Index: 561

Text #15

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3729. Min Act: -0.0000

Data Index: 1535261 (Python Code)

Max Activating Token Index: 116

Text #16

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1609878 (Python Code)

Max Activating Token Index: 619

Text #17

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3568. Min Act: -0.0000

Data Index: 1379932 (Python Code)

Max Activating Token Index: 770

Text #18

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1485097 (Python Code)

Max Activating Token Index: 97

Text #19

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3546. Min Act: -0.0000

Data Index: 759215 (C4 (Web Text))

Max Activating Token Index: 627