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

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

Neuron 5529 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2284. Min Range: -3.2284

Max Act: 2.8976. Min Act: -0.0000

Data Index: 841658 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 3.2284. Min Range: -3.2284

Max Act: 3.0970. Min Act: -0.0000

Data Index: 846822 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 3.2284. Min Range: -3.2284

Max Act: 3.2078. Min Act: -0.0000

Data Index: 1267974 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 3.2284. Min Range: -3.2284

Max Act: 3.0492. Min Act: -0.0000

Data Index: 653194 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 3.2284. Min Range: -3.2284

Max Act: 3.2284. Min Act: -0.0000

Data Index: 648073 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 3.2284. Min Range: -3.2284

Max Act: 3.0118. Min Act: -0.0000

Data Index: 224372 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 3.2284. Min Range: -3.2284

Max Act: 2.8166. Min Act: -0.0000

Data Index: 414878 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 3.2284. Min Range: -3.2284

Max Act: 2.7756. Min Act: -0.0000

Data Index: 1266146 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 3.2284. Min Range: -3.2284

Max Act: 2.8105. Min Act: -0.0000

Data Index: 114677 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 3.2284. Min Range: -3.2284

Max Act: 2.6361. Min Act: -0.0000

Data Index: 952218 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 3.2284. Min Range: -3.2284

Max Act: 2.5670. Min Act: -0.0000

Data Index: 397532 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 3.2284. Min Range: -3.2284

Max Act: 2.3625. Min Act: -0.0000

Data Index: 1256871 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 3.2284. Min Range: -3.2284

Max Act: 2.4474. Min Act: -0.0000

Data Index: 1337250 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 3.2284. Min Range: -3.2284

Max Act: 2.4081. Min Act: -0.0000

Data Index: 1202990 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 3.2284. Min Range: -3.2284

Max Act: 2.4605. Min Act: -0.0000

Data Index: 606128 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 3.2284. Min Range: -3.2284

Max Act: 2.4966. Min Act: -0.0000

Data Index: 908799 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 3.2284. Min Range: -3.2284

Max Act: 2.2559. Min Act: -0.0000

Data Index: 1292845 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 3.2284. Min Range: -3.2284

Max Act: 2.2343. Min Act: -0.0000

Data Index: 346656 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 3.2284. Min Range: -3.2284

Max Act: 2.6212. Min Act: -0.0000

Data Index: 722629 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 3.2284. Min Range: -3.2284

Max Act: 2.3431. Min Act: -0.0000

Data Index: 674713 (C4 (Web Text))

Max Activating Token Index: 283