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

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

Neuron 1129 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5525. Min Act: -0.0004

Data Index: 1640070 (Python Code)

Max Activating Token Index: 439

Text #1

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5629. Min Act: -0.0004

Data Index: 1479285 (Python Code)

Max Activating Token Index: 741

Text #2

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.6167. Min Act: -0.0004

Data Index: 1589694 (Python Code)

Max Activating Token Index: 815

Text #3

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5748. Min Act: -0.0004

Data Index: 1430613 (Python Code)

Max Activating Token Index: 750

Text #4

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5731. Min Act: -0.0004

Data Index: 1501538 (Python Code)

Max Activating Token Index: 937

Text #5

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5706. Min Act: -0.0004

Data Index: 1551283 (Python Code)

Max Activating Token Index: 976

Text #6

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5665. Min Act: -0.0004

Data Index: 1594958 (Python Code)

Max Activating Token Index: 640

Text #7

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5601. Min Act: -0.0004

Data Index: 1390582 (Python Code)

Max Activating Token Index: 644

Text #8

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5526. Min Act: -0.0004

Data Index: 1524481 (Python Code)

Max Activating Token Index: 876

Text #9

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5320. Min Act: -0.0004

Data Index: 1634470 (Python Code)

Max Activating Token Index: 484

Text #10

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5518. Min Act: -0.0004

Data Index: 1481190 (Python Code)

Max Activating Token Index: 311

Text #11

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5478. Min Act: -0.0004

Data Index: 1454276 (Python Code)

Max Activating Token Index: 1005

Text #12

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5492. Min Act: -0.0004

Data Index: 1444891 (Python Code)

Max Activating Token Index: 134

Text #13

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5266. Min Act: -0.0004

Data Index: 1587041 (Python Code)

Max Activating Token Index: 886

Text #14

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5298. Min Act: -0.0004

Data Index: 1555334 (Python Code)

Max Activating Token Index: 987

Text #15

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5242. Min Act: -0.0004

Data Index: 1556411 (Python Code)

Max Activating Token Index: 827

Text #16

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5231. Min Act: -0.0004

Data Index: 1628144 (Python Code)

Max Activating Token Index: 764

Text #17

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5387. Min Act: -0.0004

Data Index: 1615636 (Python Code)

Max Activating Token Index: 932

Text #18

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5369. Min Act: -0.0004

Data Index: 1651115 (Python Code)

Max Activating Token Index: 1014

Text #19

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5381. Min Act: -0.0004

Data Index: 1558053 (Python Code)

Max Activating Token Index: 1004