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

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

Neuron 1518 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: 1.7811. Min Range: -1.7811

Max Act: 1.7811. Min Act: -0.0000

Data Index: 272019 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.2769. Min Act: -0.0000

Data Index: 281401 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.2079. Min Act: -0.0000

Data Index: 1037296 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.2160. Min Act: -0.0000

Data Index: 290968 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.1829. Min Act: -0.0000

Data Index: 1198784 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.1366. Min Act: -0.0000

Data Index: 175792 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.1907. Min Act: -0.0000

Data Index: 766885 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.2342. Min Act: -0.0000

Data Index: 833969 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.1502. Min Act: -0.0000

Data Index: 1210972 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.1351. Min Act: -0.0000

Data Index: 800991 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.0684. Min Act: -0.0000

Data Index: 138161 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.0979. Min Act: -0.0000

Data Index: 689693 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.0152. Min Act: -0.0000

Data Index: 1508493 (Python Code)

Max Activating Token Index: 394

Text #13

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.0132. Min Act: -0.0000

Data Index: 368617 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 1.7811. Min Range: -1.7811

Max Act: 0.9468. Min Act: -0.0000

Data Index: 419960 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.0033. Min Act: -0.0000

Data Index: 591060 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 1.7811. Min Range: -1.7811

Max Act: 0.8545. Min Act: -0.0000

Data Index: 312254 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 1.7811. Min Range: -1.7811

Max Act: 1.0524. Min Act: -0.0000

Data Index: 1028563 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 1.7811. Min Range: -1.7811

Max Act: 0.9862. Min Act: -0.0000

Data Index: 590844 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 1.7811. Min Range: -1.7811

Max Act: 0.9098. Min Act: -0.0000

Data Index: 1019797 (C4 (Web Text))

Max Activating Token Index: 436