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

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

Neuron 2123 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: 3.1849. Min Range: -3.1849

Max Act: 3.1849. Min Act: -0.0000

Data Index: 79946 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 3.1849. Min Range: -3.1849

Max Act: 2.7800. Min Act: -0.0000

Data Index: 387431 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 3.1849. Min Range: -3.1849

Max Act: 2.7461. Min Act: -0.0000

Data Index: 518188 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 3.1849. Min Range: -3.1849

Max Act: 2.7328. Min Act: -0.0000

Data Index: 1160792 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 3.1849. Min Range: -3.1849

Max Act: 2.5412. Min Act: -0.0000

Data Index: 1280821 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 3.1849. Min Range: -3.1849

Max Act: 2.3220. Min Act: -0.0000

Data Index: 853514 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 3.1849. Min Range: -3.1849

Max Act: 2.3052. Min Act: -0.0000

Data Index: 19087 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 3.1849. Min Range: -3.1849

Max Act: 2.1632. Min Act: -0.0000

Data Index: 208991 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 3.1849. Min Range: -3.1849

Max Act: 2.3870. Min Act: -0.0000

Data Index: 904304 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 3.1849. Min Range: -3.1849

Max Act: 2.2001. Min Act: -0.0000

Data Index: 624969 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 3.1849. Min Range: -3.1849

Max Act: 2.1383. Min Act: -0.0000

Data Index: 201242 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 3.1849. Min Range: -3.1849

Max Act: 2.1018. Min Act: -0.0000

Data Index: 203904 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 3.1849. Min Range: -3.1849

Max Act: 2.0691. Min Act: -0.0000

Data Index: 31042 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 3.1849. Min Range: -3.1849

Max Act: 1.9149. Min Act: -0.0000

Data Index: 1275435 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 3.1849. Min Range: -3.1849

Max Act: 1.8724. Min Act: -0.0000

Data Index: 1149252 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 3.1849. Min Range: -3.1849

Max Act: 1.9814. Min Act: -0.0000

Data Index: 674291 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 3.1849. Min Range: -3.1849

Max Act: 1.9657. Min Act: -0.0000

Data Index: 268689 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 3.1849. Min Range: -3.1849

Max Act: 2.0442. Min Act: -0.0000

Data Index: 551335 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 3.1849. Min Range: -3.1849

Max Act: 2.0197. Min Act: -0.0000

Data Index: 1036943 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 3.1849. Min Range: -3.1849

Max Act: 2.0146. Min Act: -0.0000

Data Index: 1129376 (C4 (Web Text))

Max Activating Token Index: 307