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

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

Neuron 5181 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: 2.7034. Min Range: -2.7034

Max Act: 2.7034. Min Act: -0.0000

Data Index: 816531 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 2.7034. Min Range: -2.7034

Max Act: 2.2289. Min Act: -0.0000

Data Index: 344299 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 2.7034. Min Range: -2.7034

Max Act: 2.1200. Min Act: -0.0000

Data Index: 1173465 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 2.7034. Min Range: -2.7034

Max Act: 1.8613. Min Act: -0.0000

Data Index: 643527 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 2.7034. Min Range: -2.7034

Max Act: 1.8813. Min Act: -0.0000

Data Index: 633886 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 2.7034. Min Range: -2.7034

Max Act: 1.9513. Min Act: -0.0000

Data Index: 402708 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 2.7034. Min Range: -2.7034

Max Act: 1.9998. Min Act: -0.0000

Data Index: 154429 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 2.7034. Min Range: -2.7034

Max Act: 1.8460. Min Act: -0.0000

Data Index: 567440 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 2.7034. Min Range: -2.7034

Max Act: 1.7270. Min Act: -0.0000

Data Index: 844979 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 2.7034. Min Range: -2.7034

Max Act: 1.7783. Min Act: -0.0000

Data Index: 678317 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 2.7034. Min Range: -2.7034

Max Act: 1.6020. Min Act: -0.0000

Data Index: 727552 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 2.7034. Min Range: -2.7034

Max Act: 1.6890. Min Act: -0.0000

Data Index: 434119 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 2.7034. Min Range: -2.7034

Max Act: 1.6976. Min Act: -0.0000

Data Index: 110404 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 2.7034. Min Range: -2.7034

Max Act: 1.5691. Min Act: -0.0000

Data Index: 494072 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 2.7034. Min Range: -2.7034

Max Act: 1.5730. Min Act: -0.0000

Data Index: 357477 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 2.7034. Min Range: -2.7034

Max Act: 1.5631. Min Act: -0.0000

Data Index: 866872 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 2.7034. Min Range: -2.7034

Max Act: 1.5575. Min Act: -0.0000

Data Index: 1332154 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 2.7034. Min Range: -2.7034

Max Act: 1.5494. Min Act: -0.0000

Data Index: 225373 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 2.7034. Min Range: -2.7034

Max Act: 1.4404. Min Act: -0.0000

Data Index: 1053044 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 2.7034. Min Range: -2.7034

Max Act: 1.6043. Min Act: -0.0000

Data Index: 149734 (C4 (Web Text))

Max Activating Token Index: 152