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

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

Neuron 4000 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: 1.2940. Min Range: -1.2940

Max Act: 1.2940. Min Act: -0.0000

Data Index: 1451148 (Python Code)

Max Activating Token Index: 544

Text #1

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.2717. Min Act: -0.0000

Data Index: 1375033 (Python Code)

Max Activating Token Index: 183

Text #2

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.1777. Min Act: -0.0000

Data Index: 1483034 (Python Code)

Max Activating Token Index: 321

Text #3

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.0163. Min Act: -0.0000

Data Index: 1539046 (Python Code)

Max Activating Token Index: 898

Text #4

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.9583. Min Act: -0.0000

Data Index: 1575392 (Python Code)

Max Activating Token Index: 772

Text #5

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.9623. Min Act: -0.0000

Data Index: 1573191 (Python Code)

Max Activating Token Index: 686

Text #6

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.9903. Min Act: -0.0000

Data Index: 1403374 (Python Code)

Max Activating Token Index: 943

Text #7

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.9450. Min Act: -0.0000

Data Index: 1403963 (Python Code)

Max Activating Token Index: 34

Text #8

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.8659. Min Act: -0.0000

Data Index: 1502711 (Python Code)

Max Activating Token Index: 481

Text #9

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.9170. Min Act: -0.0000

Data Index: 1522870 (Python Code)

Max Activating Token Index: 32

Text #10

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.8879. Min Act: -0.0000

Data Index: 1513208 (Python Code)

Max Activating Token Index: 593

Text #11

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.9050. Min Act: -0.0000

Data Index: 1654022 (Python Code)

Max Activating Token Index: 317

Text #12

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.8990. Min Act: -0.0000

Data Index: 1440206 (Python Code)

Max Activating Token Index: 806

Text #13

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.8754. Min Act: -0.0000

Data Index: 1457724 (Python Code)

Max Activating Token Index: 852

Text #14

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.8639. Min Act: -0.0000

Data Index: 1424863 (Python Code)

Max Activating Token Index: 34

Text #15

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.8089. Min Act: -0.0000

Data Index: 1494908 (Python Code)

Max Activating Token Index: 1000

Text #16

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1630785 (Python Code)

Max Activating Token Index: 420

Text #17

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1423245 (Python Code)

Max Activating Token Index: 820

Text #18

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.8971. Min Act: -0.0000

Data Index: 1595808 (Python Code)

Max Activating Token Index: 793

Text #19

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1368544 (Python Code)

Max Activating Token Index: 785