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

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

Neuron 4360 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.5754. Min Act: -0.0000

Data Index: 79152 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.2399. Min Act: -0.0000

Data Index: 1126155 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.3199. Min Act: -0.0000

Data Index: 762247 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.2395. Min Act: -0.0000

Data Index: 663961 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.2113. Min Act: -0.0000

Data Index: 1592577 (Python Code)

Max Activating Token Index: 34

Text #5

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.2176. Min Act: -0.0000

Data Index: 1509057 (Python Code)

Max Activating Token Index: 231

Text #6

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.1714. Min Act: -0.0000

Data Index: 705255 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.1797. Min Act: -0.0000

Data Index: 525880 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.2101. Min Act: -0.0000

Data Index: 594947 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.1736. Min Act: -0.0000

Data Index: 1481749 (Python Code)

Max Activating Token Index: 41

Text #10

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.1268. Min Act: -0.0000

Data Index: 1471340 (Python Code)

Max Activating Token Index: 374

Text #11

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.0769. Min Act: -0.0000

Data Index: 477615 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.2243. Min Act: -0.0000

Data Index: 499781 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.1481. Min Act: -0.0000

Data Index: 1423151 (Python Code)

Max Activating Token Index: 240

Text #14

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.1612. Min Act: -0.0000

Data Index: 1633467 (Python Code)

Max Activating Token Index: 109

Text #15

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.1988. Min Act: -0.0000

Data Index: 741968 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.1698. Min Act: -0.0000

Data Index: 1553242 (Python Code)

Max Activating Token Index: 949

Text #17

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.0880. Min Act: -0.0000

Data Index: 858859 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.1420. Min Act: -0.0000

Data Index: 787319 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.1212. Min Act: -0.0000

Data Index: 262060 (C4 (Web Text))

Max Activating Token Index: 247