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

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

Neuron 3099 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.2036. Min Act: -0.0000

Data Index: 495121 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8438. Min Act: -0.0001

Data Index: 1197946 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1135316 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.7299. Min Act: -0.0000

Data Index: 1341261 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.6940. Min Act: -0.0000

Data Index: 113034 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.6435. Min Act: -0.0000

Data Index: 1332381 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.6594. Min Act: -0.0000

Data Index: 131625 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.5874. Min Act: -0.0001

Data Index: 203934 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1044452 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.6024. Min Act: -0.0000

Data Index: 103706 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.5748. Min Act: -0.0000

Data Index: 295304 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.5751. Min Act: -0.0001

Data Index: 188543 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1188085 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.5680. Min Act: -0.0000

Data Index: 920834 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.5849. Min Act: -0.0000

Data Index: 863517 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.6057. Min Act: -0.0001

Data Index: 683295 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.5670. Min Act: -0.0000

Data Index: 824126 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.6032. Min Act: -0.0000

Data Index: 441464 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.6346. Min Act: -0.0000

Data Index: 179344 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.5607. Min Act: -0.0000

Data Index: 309532 (C4 (Web Text))

Max Activating Token Index: 66