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

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

Neuron 3956 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: 0.9672. Min Range: -0.9672

Max Act: 0.9672. Min Act: -0.0000

Data Index: 1537654 (Python Code)

Max Activating Token Index: 518

Text #1

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1418861 (Python Code)

Max Activating Token Index: 1015

Text #2

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.9304. Min Act: -0.0000

Data Index: 1374708 (Python Code)

Max Activating Token Index: 428

Text #3

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.8477. Min Act: -0.0000

Data Index: 1556181 (Python Code)

Max Activating Token Index: 644

Text #4

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1526856 (Python Code)

Max Activating Token Index: 749

Text #5

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.8532. Min Act: -0.0000

Data Index: 1477861 (Python Code)

Max Activating Token Index: 1000

Text #6

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7258. Min Act: -0.0000

Data Index: 1428599 (Python Code)

Max Activating Token Index: 746

Text #7

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7325. Min Act: -0.0000

Data Index: 1495398 (Python Code)

Max Activating Token Index: 906

Text #8

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7260. Min Act: -0.0000

Data Index: 1449040 (Python Code)

Max Activating Token Index: 881

Text #9

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1598878 (Python Code)

Max Activating Token Index: 378

Text #10

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1400195 (Python Code)

Max Activating Token Index: 818

Text #11

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1583664 (Python Code)

Max Activating Token Index: 863

Text #12

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7083. Min Act: -0.0000

Data Index: 1544340 (Python Code)

Max Activating Token Index: 327

Text #13

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1464076 (Python Code)

Max Activating Token Index: 472

Text #14

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1469001 (Python Code)

Max Activating Token Index: 555

Text #15

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1639569 (Python Code)

Max Activating Token Index: 1007

Text #16

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.6707. Min Act: -0.0000

Data Index: 1600713 (Python Code)

Max Activating Token Index: 348

Text #17

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1511562 (Python Code)

Max Activating Token Index: 899

Text #18

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.5934. Min Act: -0.0000

Data Index: 1491371 (Python Code)

Max Activating Token Index: 852

Text #19

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.6089. Min Act: -0.0000

Data Index: 1504542 (Python Code)

Max Activating Token Index: 664