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

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

Neuron 6078 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: 5.2650. Min Range: -5.2650

Max Act: 5.2650. Min Act: -0.0000

Data Index: 1559660 (Python Code)

Max Activating Token Index: 227

Text #1

Max Range: 5.2650. Min Range: -5.2650

Max Act: 4.5187. Min Act: -0.0000

Data Index: 1473149 (Python Code)

Max Activating Token Index: 26

Text #2

Max Range: 5.2650. Min Range: -5.2650

Max Act: 4.4511. Min Act: -0.0000

Data Index: 1579022 (Python Code)

Max Activating Token Index: 11

Text #3

Max Range: 5.2650. Min Range: -5.2650

Max Act: 4.3878. Min Act: -0.0000

Data Index: 1473932 (Python Code)

Max Activating Token Index: 607

Text #4

Max Range: 5.2650. Min Range: -5.2650

Max Act: 4.1719. Min Act: -0.0000

Data Index: 1372512 (Python Code)

Max Activating Token Index: 945

Text #5

Max Range: 5.2650. Min Range: -5.2650

Max Act: 4.3177. Min Act: -0.0000

Data Index: 1611058 (Python Code)

Max Activating Token Index: 929

Text #6

Max Range: 5.2650. Min Range: -5.2650

Max Act: 4.2585. Min Act: -0.0000

Data Index: 1440818 (Python Code)

Max Activating Token Index: 10

Text #7

Max Range: 5.2650. Min Range: -5.2650

Max Act: 4.1444. Min Act: -0.0000

Data Index: 1477624 (Python Code)

Max Activating Token Index: 374

Text #8

Max Range: 5.2650. Min Range: -5.2650

Max Act: 4.0169. Min Act: -0.0000

Data Index: 1400144 (Python Code)

Max Activating Token Index: 240

Text #9

Max Range: 5.2650. Min Range: -5.2650

Max Act: 3.9927. Min Act: -0.0000

Data Index: 1487350 (Python Code)

Max Activating Token Index: 651

Text #10

Max Range: 5.2650. Min Range: -5.2650

Max Act: 3.9767. Min Act: -0.0000

Data Index: 1604324 (Python Code)

Max Activating Token Index: 68

Text #11

Max Range: 5.2650. Min Range: -5.2650

Max Act: 4.1289. Min Act: -0.0000

Data Index: 1405055 (Python Code)

Max Activating Token Index: 92

Text #12

Max Range: 5.2650. Min Range: -5.2650

Max Act: 3.9596. Min Act: -0.0000

Data Index: 1493146 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 5.2650. Min Range: -5.2650

Max Act: 3.9583. Min Act: -0.0000

Data Index: 1483427 (Python Code)

Max Activating Token Index: 590

Text #14

Max Range: 5.2650. Min Range: -5.2650

Max Act: 4.0959. Min Act: -0.0000

Data Index: 1368222 (Python Code)

Max Activating Token Index: 535

Text #15

Max Range: 5.2650. Min Range: -5.2650

Max Act: 3.9228. Min Act: -0.0000

Data Index: 1639669 (Python Code)

Max Activating Token Index: 458

Text #16

Max Range: 5.2650. Min Range: -5.2650

Max Act: 3.7200. Min Act: -0.0000

Data Index: 1412694 (Python Code)

Max Activating Token Index: 326

Text #17

Max Range: 5.2650. Min Range: -5.2650

Max Act: 3.7141. Min Act: -0.0000

Data Index: 1574681 (Python Code)

Max Activating Token Index: 846

Text #18

Max Range: 5.2650. Min Range: -5.2650

Max Act: 3.8646. Min Act: -0.0000

Data Index: 1599381 (Python Code)

Max Activating Token Index: 588

Text #19

Max Range: 5.2650. Min Range: -5.2650

Max Act: 3.8541. Min Act: -0.0000

Data Index: 1422508 (Python Code)

Max Activating Token Index: 245