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

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

Neuron 5394 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2263. Min Act: -0.0000

Data Index: 844087 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1215876 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2084. Min Act: -0.0000

Data Index: 1062242 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1937. Min Act: -0.0000

Data Index: 204346 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2007. Min Act: -0.0000

Data Index: 859589 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1991. Min Act: -0.0000

Data Index: 1241200 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1983. Min Act: -0.0000

Data Index: 888783 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1975. Min Act: -0.0000

Data Index: 1112432 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1963. Min Act: -0.0000

Data Index: 476955 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1899. Min Act: -0.0000

Data Index: 760058 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1872. Min Act: -0.0000

Data Index: 669157 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1811. Min Act: -0.0000

Data Index: 83283 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1936. Min Act: -0.0000

Data Index: 213411 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1874. Min Act: -0.0000

Data Index: 963095 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1838. Min Act: -0.0000

Data Index: 291620 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1915. Min Act: -0.0000

Data Index: 1100224 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1825. Min Act: -0.0000

Data Index: 126358 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1808. Min Act: -0.0000

Data Index: 906190 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1822. Min Act: -0.0000

Data Index: 1341278 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1855. Min Act: -0.0000

Data Index: 944742 (C4 (Web Text))

Max Activating Token Index: 1012