Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2253 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.7560. Min Act: -0.0000

Data Index: 1555073 (Python Code)

Max Activating Token Index: 307

Text #1

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.6030. Min Act: -0.0000

Data Index: 1394099 (Python Code)

Max Activating Token Index: 381

Text #2

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.5129. Min Act: -0.0000

Data Index: 1496764 (Python Code)

Max Activating Token Index: 363

Text #3

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.3339. Min Act: -0.0000

Data Index: 1592487 (Python Code)

Max Activating Token Index: 357

Text #4

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.3855. Min Act: -0.0000

Data Index: 1590515 (Python Code)

Max Activating Token Index: 163

Text #5

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.2702. Min Act: -0.0000

Data Index: 1636718 (Python Code)

Max Activating Token Index: 209

Text #6

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.2522. Min Act: -0.0000

Data Index: 1589959 (Python Code)

Max Activating Token Index: 585

Text #7

Max Range: 3.7560. Min Range: -3.7560

Max Act: 2.9783. Min Act: -0.0000

Data Index: 1402163 (Python Code)

Max Activating Token Index: 444

Text #8

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.0808. Min Act: -0.0000

Data Index: 1360219 (Python Code)

Max Activating Token Index: 726

Text #9

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.0743. Min Act: -0.0000

Data Index: 1486153 (Python Code)

Max Activating Token Index: 639

Text #10

Max Range: 3.7560. Min Range: -3.7560

Max Act: 2.6767. Min Act: -0.0000

Data Index: 1511976 (Python Code)

Max Activating Token Index: 177

Text #11

Max Range: 3.7560. Min Range: -3.7560

Max Act: 2.9199. Min Act: -0.0000

Data Index: 1603037 (Python Code)

Max Activating Token Index: 60

Text #12

Max Range: 3.7560. Min Range: -3.7560

Max Act: 2.8871. Min Act: -0.0000

Data Index: 1389463 (Python Code)

Max Activating Token Index: 103

Text #13

Max Range: 3.7560. Min Range: -3.7560

Max Act: 2.9010. Min Act: -0.0000

Data Index: 1582383 (Python Code)

Max Activating Token Index: 176

Text #14

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.0323. Min Act: -0.0000

Data Index: 1631672 (Python Code)

Max Activating Token Index: 952

Text #15

Max Range: 3.7560. Min Range: -3.7560

Max Act: 2.7145. Min Act: -0.0000

Data Index: 1507410 (Python Code)

Max Activating Token Index: 685

Text #16

Max Range: 3.7560. Min Range: -3.7560

Max Act: 2.8314. Min Act: -0.0000

Data Index: 1648729 (Python Code)

Max Activating Token Index: 712

Text #17

Max Range: 3.7560. Min Range: -3.7560

Max Act: 2.6671. Min Act: -0.0000

Data Index: 1426337 (Python Code)

Max Activating Token Index: 151

Text #18

Max Range: 3.7560. Min Range: -3.7560

Max Act: 2.7722. Min Act: -0.0000

Data Index: 1634132 (Python Code)

Max Activating Token Index: 475

Text #19

Max Range: 3.7560. Min Range: -3.7560

Max Act: 2.6136. Min Act: -0.0000

Data Index: 1527830 (Python Code)

Max Activating Token Index: 513