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

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

Neuron 4817 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2748. Min Range: -1.2748

Max Act: 1.2748. Min Act: -0.0001

Data Index: 484952 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 1.2748. Min Range: -1.2748

Max Act: 1.2079. Min Act: -0.0001

Data Index: 663064 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 1.2748. Min Range: -1.2748

Max Act: 1.1240. Min Act: -0.0001

Data Index: 828139 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 1.2748. Min Range: -1.2748

Max Act: 1.1618. Min Act: -0.0001

Data Index: 855188 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 1.2748. Min Range: -1.2748

Max Act: 1.1644. Min Act: -0.0001

Data Index: 611239 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 1.2748. Min Range: -1.2748

Max Act: 1.0102. Min Act: -0.0001

Data Index: 1014563 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 1.2748. Min Range: -1.2748

Max Act: 1.0597. Min Act: -0.0001

Data Index: 822465 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 1.2748. Min Range: -1.2748

Max Act: 1.0529. Min Act: -0.0001

Data Index: 520706 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 1.2748. Min Range: -1.2748

Max Act: 1.0502. Min Act: -0.0001

Data Index: 975186 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 1.2748. Min Range: -1.2748

Max Act: 0.9640. Min Act: -0.0001

Data Index: 630220 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 1.2748. Min Range: -1.2748

Max Act: 1.0040. Min Act: -0.0001

Data Index: 638878 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 1.2748. Min Range: -1.2748

Max Act: 0.9992. Min Act: -0.0001

Data Index: 1162712 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 1.2748. Min Range: -1.2748

Max Act: 1.0195. Min Act: -0.0001

Data Index: 597764 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 1.2748. Min Range: -1.2748

Max Act: 0.9819. Min Act: -0.0001

Data Index: 1078899 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 1.2748. Min Range: -1.2748

Max Act: 0.9081. Min Act: -0.0001

Data Index: 200151 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 1.2748. Min Range: -1.2748

Max Act: 0.9406. Min Act: -0.0001

Data Index: 642087 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 1.2748. Min Range: -1.2748

Max Act: 0.8938. Min Act: -0.0001

Data Index: 191078 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 1.2748. Min Range: -1.2748

Max Act: 0.9151. Min Act: -0.0001

Data Index: 405695 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 1.2748. Min Range: -1.2748

Max Act: 0.9385. Min Act: -0.0001

Data Index: 560503 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 1.2748. Min Range: -1.2748

Max Act: 0.9070. Min Act: -0.0001

Data Index: 1047886 (C4 (Web Text))

Max Activating Token Index: 677