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

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

Neuron 5160 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: 1.5427. Min Range: -1.5427

Max Act: 1.5427. Min Act: -0.0000

Data Index: 1000764 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.4097. Min Act: -0.0000

Data Index: 1161393 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1647325 (Python Code)

Max Activating Token Index: 63

Text #3

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.0268. Min Act: -0.0000

Data Index: 1377580 (Python Code)

Max Activating Token Index: 16

Text #4

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.0184. Min Act: -0.0001

Data Index: 355712 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.9525. Min Act: -0.0000

Data Index: 932997 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.9568. Min Act: -0.0000

Data Index: 1369285 (Python Code)

Max Activating Token Index: 803

Text #7

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.9496. Min Act: -0.0000

Data Index: 1654103 (Python Code)

Max Activating Token Index: 535

Text #8

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.9172. Min Act: -0.0000

Data Index: 866297 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.0023. Min Act: -0.0000

Data Index: 1537631 (Python Code)

Max Activating Token Index: 636

Text #10

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.9083. Min Act: -0.0000

Data Index: 1483175 (Python Code)

Max Activating Token Index: 926

Text #11

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.9837. Min Act: -0.0000

Data Index: 1484029 (Python Code)

Max Activating Token Index: 144

Text #12

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.9189. Min Act: -0.0000

Data Index: 1400432 (Python Code)

Max Activating Token Index: 21

Text #13

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.9146. Min Act: -0.0000

Data Index: 1128305 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.9950. Min Act: -0.0000

Data Index: 1483104 (Python Code)

Max Activating Token Index: 117

Text #15

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.9092. Min Act: -0.0000

Data Index: 1596784 (Python Code)

Max Activating Token Index: 251

Text #16

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.8778. Min Act: -0.0000

Data Index: 256579 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.8698. Min Act: -0.0000

Data Index: 1339477 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.8931. Min Act: -0.0001

Data Index: 945901 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.8963. Min Act: -0.0000

Data Index: 1596539 (Python Code)

Max Activating Token Index: 511