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

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

Neuron 2509 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5499. Min Range: -2.5499

Max Act: 2.1213. Min Act: -0.0000

Data Index: 950483 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 2.5499. Min Range: -2.5499

Max Act: 2.5499. Min Act: -0.0000

Data Index: 1425603 (Python Code)

Max Activating Token Index: 104

Text #2

Max Range: 2.5499. Min Range: -2.5499

Max Act: 2.3512. Min Act: -0.0000

Data Index: 1610724 (Python Code)

Max Activating Token Index: 467

Text #3

Max Range: 2.5499. Min Range: -2.5499

Max Act: 2.3146. Min Act: -0.0000

Data Index: 1058086 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 2.5499. Min Range: -2.5499

Max Act: 2.1832. Min Act: -0.0000

Data Index: 1427446 (Python Code)

Max Activating Token Index: 854

Text #5

Max Range: 2.5499. Min Range: -2.5499

Max Act: 1.9153. Min Act: -0.0000

Data Index: 695684 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 2.5499. Min Range: -2.5499

Max Act: 1.9325. Min Act: -0.0000

Data Index: 612158 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 2.5499. Min Range: -2.5499

Max Act: 1.8924. Min Act: -0.0000

Data Index: 1492607 (Python Code)

Max Activating Token Index: 348

Text #8

Max Range: 2.5499. Min Range: -2.5499

Max Act: 2.0087. Min Act: -0.0000

Data Index: 814475 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 2.5499. Min Range: -2.5499

Max Act: 1.8690. Min Act: -0.0000

Data Index: 239466 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 2.5499. Min Range: -2.5499

Max Act: 1.9251. Min Act: -0.0000

Data Index: 661456 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 2.5499. Min Range: -2.5499

Max Act: 1.8119. Min Act: -0.0000

Data Index: 1186202 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 2.5499. Min Range: -2.5499

Max Act: 1.7144. Min Act: -0.0000

Data Index: 174131 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 2.5499. Min Range: -2.5499

Max Act: 1.8202. Min Act: -0.0000

Data Index: 768906 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 2.5499. Min Range: -2.5499

Max Act: 1.7732. Min Act: -0.0000

Data Index: 196556 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 2.5499. Min Range: -2.5499

Max Act: 1.7920. Min Act: -0.0000

Data Index: 1058370 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 2.5499. Min Range: -2.5499

Max Act: 1.8202. Min Act: -0.0000

Data Index: 1607647 (Python Code)

Max Activating Token Index: 60

Text #17

Max Range: 2.5499. Min Range: -2.5499

Max Act: 1.7362. Min Act: -0.0000

Data Index: 1256562 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 2.5499. Min Range: -2.5499

Max Act: 1.5214. Min Act: -0.0000

Data Index: 938638 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 2.5499. Min Range: -2.5499

Max Act: 1.6136. Min Act: -0.0000

Data Index: 363474 (C4 (Web Text))

Max Activating Token Index: 758