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

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

Neuron 1220 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: 1.0243. Min Range: -1.0243

Max Act: 1.0243. Min Act: -0.0000

Data Index: 1582616 (Python Code)

Max Activating Token Index: 59

Text #1

Max Range: 1.0243. Min Range: -1.0243

Max Act: 1.0006. Min Act: -0.0000

Data Index: 1380283 (Python Code)

Max Activating Token Index: 132

Text #2

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8673. Min Act: -0.0000

Data Index: 1628796 (Python Code)

Max Activating Token Index: 374

Text #3

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.9186. Min Act: -0.0000

Data Index: 1413682 (Python Code)

Max Activating Token Index: 935

Text #4

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.9145. Min Act: -0.0000

Data Index: 1555142 (Python Code)

Max Activating Token Index: 840

Text #5

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8866. Min Act: -0.0000

Data Index: 1387338 (Python Code)

Max Activating Token Index: 834

Text #6

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8996. Min Act: -0.0000

Data Index: 1584545 (Python Code)

Max Activating Token Index: 846

Text #7

Max Range: 1.0243. Min Range: -1.0243

Max Act: 1.0112. Min Act: -0.0000

Data Index: 1394273 (Python Code)

Max Activating Token Index: 883

Text #8

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8671. Min Act: -0.0000

Data Index: 1624498 (Python Code)

Max Activating Token Index: 918

Text #9

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8959. Min Act: -0.0000

Data Index: 1588348 (Python Code)

Max Activating Token Index: 746

Text #10

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1541203 (Python Code)

Max Activating Token Index: 880

Text #11

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.9203. Min Act: -0.0000

Data Index: 1433149 (Python Code)

Max Activating Token Index: 949

Text #12

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.9212. Min Act: -0.0000

Data Index: 1515382 (Python Code)

Max Activating Token Index: 528

Text #13

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8578. Min Act: -0.0000

Data Index: 1572049 (Python Code)

Max Activating Token Index: 683

Text #14

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.9306. Min Act: -0.0000

Data Index: 1616452 (Python Code)

Max Activating Token Index: 575

Text #15

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1408190 (Python Code)

Max Activating Token Index: 561

Text #16

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8985. Min Act: -0.0000

Data Index: 1647333 (Python Code)

Max Activating Token Index: 1004

Text #17

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8457. Min Act: -0.0000

Data Index: 1431018 (Python Code)

Max Activating Token Index: 873

Text #18

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.9240. Min Act: -0.0000

Data Index: 1487049 (Python Code)

Max Activating Token Index: 767

Text #19

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8114. Min Act: -0.0000

Data Index: 1573602 (Python Code)

Max Activating Token Index: 937