Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5096 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.6083. Min Range: -4.6083

Max Act: 4.6083. Min Act: -0.0000

Data Index: 1407540 (Python Code)

Max Activating Token Index: 699

Text #1

Max Range: 4.6083. Min Range: -4.6083

Max Act: 4.0196. Min Act: -0.0000

Data Index: 1637321 (Python Code)

Max Activating Token Index: 522

Text #2

Max Range: 4.6083. Min Range: -4.6083

Max Act: 3.8076. Min Act: -0.0000

Data Index: 1614747 (Python Code)

Max Activating Token Index: 460

Text #3

Max Range: 4.6083. Min Range: -4.6083

Max Act: 3.4090. Min Act: -0.0000

Data Index: 1596588 (Python Code)

Max Activating Token Index: 885

Text #4

Max Range: 4.6083. Min Range: -4.6083

Max Act: 3.3586. Min Act: -0.0000

Data Index: 1554759 (Python Code)

Max Activating Token Index: 875

Text #5

Max Range: 4.6083. Min Range: -4.6083

Max Act: 3.1901. Min Act: 0.0000

Data Index: 1370992 (Python Code)

Max Activating Token Index: 945

Text #6

Max Range: 4.6083. Min Range: -4.6083

Max Act: 2.8153. Min Act: -0.0000

Data Index: 1527040 (Python Code)

Max Activating Token Index: 390

Text #7

Max Range: 4.6083. Min Range: -4.6083

Max Act: 2.9640. Min Act: -0.0000

Data Index: 1567724 (Python Code)

Max Activating Token Index: 577

Text #8

Max Range: 4.6083. Min Range: -4.6083

Max Act: 2.9727. Min Act: -0.0000

Data Index: 1548146 (Python Code)

Max Activating Token Index: 1017

Text #9

Max Range: 4.6083. Min Range: -4.6083

Max Act: 2.9545. Min Act: -0.0000

Data Index: 1366386 (Python Code)

Max Activating Token Index: 117

Text #10

Max Range: 4.6083. Min Range: -4.6083

Max Act: 2.9391. Min Act: -0.0000

Data Index: 1370924 (Python Code)

Max Activating Token Index: 987

Text #11

Max Range: 4.6083. Min Range: -4.6083

Max Act: 2.7332. Min Act: -0.0000

Data Index: 1651686 (Python Code)

Max Activating Token Index: 988

Text #12

Max Range: 4.6083. Min Range: -4.6083

Max Act: 2.7305. Min Act: -0.0000

Data Index: 1652543 (Python Code)

Max Activating Token Index: 1006

Text #13

Max Range: 4.6083. Min Range: -4.6083

Max Act: 2.8358. Min Act: -0.0000

Data Index: 1565414 (Python Code)

Max Activating Token Index: 821

Text #14

Max Range: 4.6083. Min Range: -4.6083

Max Act: 2.6741. Min Act: -0.0000

Data Index: 1574572 (Python Code)

Max Activating Token Index: 833

Text #15

Max Range: 4.6083. Min Range: -4.6083

Max Act: 2.7689. Min Act: -0.0000

Data Index: 1474592 (Python Code)

Max Activating Token Index: 494

Text #16

Max Range: 4.6083. Min Range: -4.6083

Max Act: 2.8439. Min Act: -0.0000

Data Index: 1365321 (Python Code)

Max Activating Token Index: 243

Text #17

Max Range: 4.6083. Min Range: -4.6083

Max Act: 2.5423. Min Act: -0.0000

Data Index: 1366548 (Python Code)

Max Activating Token Index: 977

Text #18

Max Range: 4.6083. Min Range: -4.6083

Max Act: 2.4956. Min Act: 0.0001

Data Index: 1641437 (Python Code)

Max Activating Token Index: 348

Text #19

Max Range: 4.6083. Min Range: -4.6083

Max Act: 2.7728. Min Act: -0.0000

Data Index: 1600373 (Python Code)

Max Activating Token Index: 948