Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1962 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.4872. Min Act: -0.0003

Data Index: 1398307 (Python Code)

Max Activating Token Index: 295

Text #1

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.5010. Min Act: -0.0003

Data Index: 1617115 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.4843. Min Act: -0.0003

Data Index: 1490036 (Python Code)

Max Activating Token Index: 178

Text #3

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.4770. Min Act: -0.0003

Data Index: 1574880 (Python Code)

Max Activating Token Index: 744

Text #4

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.4660. Min Act: -0.0003

Data Index: 1568880 (Python Code)

Max Activating Token Index: 380

Text #5

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.4461. Min Act: -0.0003

Data Index: 1472100 (Python Code)

Max Activating Token Index: 956

Text #6

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.4962. Min Act: -0.0003

Data Index: 1380387 (Python Code)

Max Activating Token Index: 368

Text #7

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.4353. Min Act: -0.0003

Data Index: 1595380 (Python Code)

Max Activating Token Index: 682

Text #8

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3915. Min Act: -0.0003

Data Index: 1626937 (Python Code)

Max Activating Token Index: 290

Text #9

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.4263. Min Act: -0.0003

Data Index: 1634034 (Python Code)

Max Activating Token Index: 181

Text #10

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.4483. Min Act: -0.0003

Data Index: 1404470 (Python Code)

Max Activating Token Index: 943

Text #11

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.4648. Min Act: -0.0003

Data Index: 1439693 (Python Code)

Max Activating Token Index: 86

Text #12

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.4285. Min Act: -0.0003

Data Index: 1367553 (Python Code)

Max Activating Token Index: 998

Text #13

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.4125. Min Act: -0.0003

Data Index: 1539810 (Python Code)

Max Activating Token Index: 959

Text #14

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.4282. Min Act: -0.0003

Data Index: 1642895 (Python Code)

Max Activating Token Index: 540

Text #15

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.4276. Min Act: -0.0003

Data Index: 1453545 (Python Code)

Max Activating Token Index: 75

Text #16

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.4416. Min Act: -0.0003

Data Index: 1445253 (Python Code)

Max Activating Token Index: 722

Text #17

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.4203. Min Act: -0.0003

Data Index: 1557767 (Python Code)

Max Activating Token Index: 645

Text #18

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3962. Min Act: -0.0003

Data Index: 1596733 (Python Code)

Max Activating Token Index: 907

Text #19

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.4067. Min Act: -0.0003

Data Index: 1644272 (Python Code)

Max Activating Token Index: 993