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

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

Neuron 3299 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: 0.4290. Min Range: -0.4290

Max Act: 0.4290. Min Act: -0.0000

Data Index: 732727 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3982. Min Act: -0.0000

Data Index: 784839 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3891. Min Act: -0.0000

Data Index: 1073101 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.4126. Min Act: -0.0000

Data Index: 1010092 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3681. Min Act: -0.0000

Data Index: 369847 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3895. Min Act: -0.0000

Data Index: 673158 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2910. Min Act: -0.0000

Data Index: 1520608 (Python Code)

Max Activating Token Index: 199

Text #7

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2233. Min Act: -0.0000

Data Index: 772188 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1656140 (Python Code)

Max Activating Token Index: 792

Text #9

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2191. Min Act: -0.0000

Data Index: 136586 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2183. Min Act: -0.0000

Data Index: 397973 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1256778 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2093. Min Act: -0.0000

Data Index: 949377 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.1899. Min Act: -0.0000

Data Index: 810090 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2009. Min Act: -0.0000

Data Index: 1175087 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1140469 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1133078 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2010. Min Act: -0.0000

Data Index: 314780 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.1980. Min Act: -0.0000

Data Index: 928258 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.2018. Min Act: -0.0000

Data Index: 1600997 (Python Code)

Max Activating Token Index: 425