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

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

Neuron 5542 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9148. Min Range: -2.9148

Max Act: 2.9148. Min Act: -0.0000

Data Index: 1538168 (Python Code)

Max Activating Token Index: 984

Text #1

Max Range: 2.9148. Min Range: -2.9148

Max Act: 2.2639. Min Act: -0.0000

Data Index: 1554103 (Python Code)

Max Activating Token Index: 912

Text #2

Max Range: 2.9148. Min Range: -2.9148

Max Act: 2.6206. Min Act: -0.0000

Data Index: 1621959 (Python Code)

Max Activating Token Index: 847

Text #3

Max Range: 2.9148. Min Range: -2.9148

Max Act: 2.3609. Min Act: -0.0000

Data Index: 1376070 (Python Code)

Max Activating Token Index: 164

Text #4

Max Range: 2.9148. Min Range: -2.9148

Max Act: 2.5702. Min Act: -0.0000

Data Index: 1532772 (Python Code)

Max Activating Token Index: 150

Text #5

Max Range: 2.9148. Min Range: -2.9148

Max Act: 2.2675. Min Act: -0.0000

Data Index: 1531959 (Python Code)

Max Activating Token Index: 102

Text #6

Max Range: 2.9148. Min Range: -2.9148

Max Act: 2.3611. Min Act: -0.0000

Data Index: 1602630 (Python Code)

Max Activating Token Index: 918

Text #7

Max Range: 2.9148. Min Range: -2.9148

Max Act: 2.1594. Min Act: -0.0000

Data Index: 1585834 (Python Code)

Max Activating Token Index: 159

Text #8

Max Range: 2.9148. Min Range: -2.9148

Max Act: 2.1169. Min Act: -0.0000

Data Index: 1378636 (Python Code)

Max Activating Token Index: 447

Text #9

Max Range: 2.9148. Min Range: -2.9148

Max Act: 2.3206. Min Act: -0.0000

Data Index: 1426466 (Python Code)

Max Activating Token Index: 29

Text #10

Max Range: 2.9148. Min Range: -2.9148

Max Act: 2.1775. Min Act: -0.0000

Data Index: 1625965 (Python Code)

Max Activating Token Index: 655

Text #11

Max Range: 2.9148. Min Range: -2.9148

Max Act: 2.2949. Min Act: -0.0000

Data Index: 1537711 (Python Code)

Max Activating Token Index: 530

Text #12

Max Range: 2.9148. Min Range: -2.9148

Max Act: 2.2064. Min Act: -0.0000

Data Index: 1432042 (Python Code)

Max Activating Token Index: 742

Text #13

Max Range: 2.9148. Min Range: -2.9148

Max Act: 1.9012. Min Act: -0.0000

Data Index: 1611466 (Python Code)

Max Activating Token Index: 994

Text #14

Max Range: 2.9148. Min Range: -2.9148

Max Act: 2.0000. Min Act: -0.0000

Data Index: 1414064 (Python Code)

Max Activating Token Index: 564

Text #15

Max Range: 2.9148. Min Range: -2.9148

Max Act: 2.2188. Min Act: -0.0000

Data Index: 1454979 (Python Code)

Max Activating Token Index: 346

Text #16

Max Range: 2.9148. Min Range: -2.9148

Max Act: 2.1019. Min Act: -0.0000

Data Index: 1565477 (Python Code)

Max Activating Token Index: 639

Text #17

Max Range: 2.9148. Min Range: -2.9148

Max Act: 2.1156. Min Act: -0.0000

Data Index: 1488514 (Python Code)

Max Activating Token Index: 804

Text #18

Max Range: 2.9148. Min Range: -2.9148

Max Act: 1.9865. Min Act: -0.0000

Data Index: 1389113 (Python Code)

Max Activating Token Index: 427

Text #19

Max Range: 2.9148. Min Range: -2.9148

Max Act: 1.5478. Min Act: -0.0000

Data Index: 1542575 (Python Code)

Max Activating Token Index: 890