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

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

Neuron 766 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1865. Min Range: -2.1865

Max Act: 2.1865. Min Act: -0.0000

Data Index: 947338 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 2.1865. Min Range: -2.1865

Max Act: 2.1404. Min Act: 0.0000

Data Index: 242669 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 2.1865. Min Range: -2.1865

Max Act: 1.8232. Min Act: -0.0000

Data Index: 196180 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 2.1865. Min Range: -2.1865

Max Act: 1.9166. Min Act: 0.0000

Data Index: 344388 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 2.1865. Min Range: -2.1865

Max Act: 1.7592. Min Act: 0.0000

Data Index: 1282908 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 2.1865. Min Range: -2.1865

Max Act: 1.6524. Min Act: -0.0000

Data Index: 813538 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 2.1865. Min Range: -2.1865

Max Act: 1.6000. Min Act: 0.0000

Data Index: 664003 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 2.1865. Min Range: -2.1865

Max Act: 1.6952. Min Act: -0.0000

Data Index: 1236925 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 2.1865. Min Range: -2.1865

Max Act: 1.5404. Min Act: -0.0000

Data Index: 1024169 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 2.1865. Min Range: -2.1865

Max Act: 1.6237. Min Act: -0.0000

Data Index: 1356334 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 2.1865. Min Range: -2.1865

Max Act: 1.5215. Min Act: -0.0000

Data Index: 756024 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 2.1865. Min Range: -2.1865

Max Act: 1.6794. Min Act: -0.0000

Data Index: 465335 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 2.1865. Min Range: -2.1865

Max Act: 1.4261. Min Act: -0.0000

Data Index: 127809 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 2.1865. Min Range: -2.1865

Max Act: 1.3978. Min Act: 0.0000

Data Index: 629128 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 2.1865. Min Range: -2.1865

Max Act: 1.3987. Min Act: 0.0002

Data Index: 837532 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 2.1865. Min Range: -2.1865

Max Act: 1.3862. Min Act: -0.0000

Data Index: 530442 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 2.1865. Min Range: -2.1865

Max Act: 1.3558. Min Act: -0.0000

Data Index: 1019044 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 2.1865. Min Range: -2.1865

Max Act: 1.3534. Min Act: -0.0000

Data Index: 299051 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 2.1865. Min Range: -2.1865

Max Act: 1.3525. Min Act: 0.0000

Data Index: 1260147 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 2.1865. Min Range: -2.1865

Max Act: 1.3269. Min Act: -0.0000

Data Index: 143497 (C4 (Web Text))

Max Activating Token Index: 494