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

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

Neuron 5651 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3606. Min Range: -1.3606

Max Act: 1.3606. Min Act: -0.0000

Data Index: 1601346 (Python Code)

Max Activating Token Index: 139

Text #1

Max Range: 1.3606. Min Range: -1.3606

Max Act: 1.0653. Min Act: -0.0000

Data Index: 1655732 (Python Code)

Max Activating Token Index: 694

Text #2

Max Range: 1.3606. Min Range: -1.3606

Max Act: 1.1311. Min Act: -0.0000

Data Index: 1544277 (Python Code)

Max Activating Token Index: 1019

Text #3

Max Range: 1.3606. Min Range: -1.3606

Max Act: 1.1231. Min Act: -0.0000

Data Index: 1439671 (Python Code)

Max Activating Token Index: 81

Text #4

Max Range: 1.3606. Min Range: -1.3606

Max Act: 1.2077. Min Act: -0.0000

Data Index: 1374818 (Python Code)

Max Activating Token Index: 169

Text #5

Max Range: 1.3606. Min Range: -1.3606

Max Act: 1.2227. Min Act: -0.0000

Data Index: 1574327 (Python Code)

Max Activating Token Index: 695

Text #6

Max Range: 1.3606. Min Range: -1.3606

Max Act: 1.2463. Min Act: -0.0000

Data Index: 1611880 (Python Code)

Max Activating Token Index: 619

Text #7

Max Range: 1.3606. Min Range: -1.3606

Max Act: 1.2148. Min Act: -0.0000

Data Index: 1596497 (Python Code)

Max Activating Token Index: 264

Text #8

Max Range: 1.3606. Min Range: -1.3606

Max Act: 1.0995. Min Act: -0.0000

Data Index: 1549352 (Python Code)

Max Activating Token Index: 606

Text #9

Max Range: 1.3606. Min Range: -1.3606

Max Act: 1.0741. Min Act: -0.0000

Data Index: 1445571 (Python Code)

Max Activating Token Index: 459

Text #10

Max Range: 1.3606. Min Range: -1.3606

Max Act: 1.0857. Min Act: -0.0000

Data Index: 950000 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 1.3606. Min Range: -1.3606

Max Act: 1.0549. Min Act: -0.0000

Data Index: 46203 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 1.3606. Min Range: -1.3606

Max Act: 1.0032. Min Act: -0.0000

Data Index: 1532483 (Python Code)

Max Activating Token Index: 661

Text #13

Max Range: 1.3606. Min Range: -1.3606

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1581335 (Python Code)

Max Activating Token Index: 91

Text #14

Max Range: 1.3606. Min Range: -1.3606

Max Act: 0.9548. Min Act: -0.0000

Data Index: 1572526 (Python Code)

Max Activating Token Index: 775

Text #15

Max Range: 1.3606. Min Range: -1.3606

Max Act: 1.0652. Min Act: -0.0000

Data Index: 1530007 (Python Code)

Max Activating Token Index: 1007

Text #16

Max Range: 1.3606. Min Range: -1.3606

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1446964 (Python Code)

Max Activating Token Index: 989

Text #17

Max Range: 1.3606. Min Range: -1.3606

Max Act: 0.9229. Min Act: -0.0000

Data Index: 1612546 (Python Code)

Max Activating Token Index: 170

Text #18

Max Range: 1.3606. Min Range: -1.3606

Max Act: 0.9534. Min Act: -0.0000

Data Index: 1516882 (Python Code)

Max Activating Token Index: 1006

Text #19

Max Range: 1.3606. Min Range: -1.3606

Max Act: 0.9570. Min Act: -0.0000

Data Index: 1538584 (Python Code)

Max Activating Token Index: 466