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

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

Neuron 2046 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6137. Min Range: -0.6137

Max Act: 0.6137. Min Act: -0.0000

Data Index: 1585152 (Python Code)

Max Activating Token Index: 827

Text #1

Max Range: 0.6137. Min Range: -0.6137

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1522621 (Python Code)

Max Activating Token Index: 870

Text #2

Max Range: 0.6137. Min Range: -0.6137

Max Act: 0.5477. Min Act: -0.0000

Data Index: 47513 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.6137. Min Range: -0.6137

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1362093 (Python Code)

Max Activating Token Index: 885

Text #4

Max Range: 0.6137. Min Range: -0.6137

Max Act: 0.4762. Min Act: -0.0000

Data Index: 930909 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.6137. Min Range: -0.6137

Max Act: 0.4461. Min Act: -0.0000

Data Index: 1532889 (Python Code)

Max Activating Token Index: 730

Text #6

Max Range: 0.6137. Min Range: -0.6137

Max Act: 0.4605. Min Act: -0.0000

Data Index: 1067856 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.6137. Min Range: -0.6137

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1365515 (Python Code)

Max Activating Token Index: 975

Text #8

Max Range: 0.6137. Min Range: -0.6137

Max Act: 0.4256. Min Act: -0.0000

Data Index: 898762 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.6137. Min Range: -0.6137

Max Act: 0.4487. Min Act: -0.0000

Data Index: 630133 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.6137. Min Range: -0.6137

Max Act: 0.4215. Min Act: -0.0000

Data Index: 1020219 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 0.6137. Min Range: -0.6137

Max Act: 0.4239. Min Act: -0.0000

Data Index: 1587855 (Python Code)

Max Activating Token Index: 1000

Text #12

Max Range: 0.6137. Min Range: -0.6137

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1463601 (Python Code)

Max Activating Token Index: 884

Text #13

Max Range: 0.6137. Min Range: -0.6137

Max Act: 0.4769. Min Act: -0.0000

Data Index: 1574505 (Python Code)

Max Activating Token Index: 933

Text #14

Max Range: 0.6137. Min Range: -0.6137

Max Act: 0.4396. Min Act: -0.0000

Data Index: 1528286 (Python Code)

Max Activating Token Index: 837

Text #15

Max Range: 0.6137. Min Range: -0.6137

Max Act: 0.4205. Min Act: -0.0000

Data Index: 219008 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.6137. Min Range: -0.6137

Max Act: 0.4341. Min Act: -0.0000

Data Index: 944001 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.6137. Min Range: -0.6137

Max Act: 0.3648. Min Act: -0.0000

Data Index: 1414279 (Python Code)

Max Activating Token Index: 1015

Text #18

Max Range: 0.6137. Min Range: -0.6137

Max Act: 0.3868. Min Act: -0.0000

Data Index: 1305883 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.6137. Min Range: -0.6137

Max Act: 0.3999. Min Act: -0.0000

Data Index: 1570911 (Python Code)

Max Activating Token Index: 788