Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3506 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.1085. Min Range: -3.1085

Max Act: 3.0990. Min Act: -0.0000

Data Index: 1633516 (Python Code)

Max Activating Token Index: 743

Text #1

Max Range: 3.1085. Min Range: -3.1085

Max Act: 3.1085. Min Act: -0.0000

Data Index: 1607401 (Python Code)

Max Activating Token Index: 752

Text #2

Max Range: 3.1085. Min Range: -3.1085

Max Act: 2.9733. Min Act: -0.0000

Data Index: 1420852 (Python Code)

Max Activating Token Index: 1003

Text #3

Max Range: 3.1085. Min Range: -3.1085

Max Act: 3.0924. Min Act: -0.0000

Data Index: 1596774 (Python Code)

Max Activating Token Index: 722

Text #4

Max Range: 3.1085. Min Range: -3.1085

Max Act: 3.0246. Min Act: -0.0000

Data Index: 1479360 (Python Code)

Max Activating Token Index: 867

Text #5

Max Range: 3.1085. Min Range: -3.1085

Max Act: 2.6884. Min Act: -0.0000

Data Index: 1465188 (Python Code)

Max Activating Token Index: 592

Text #6

Max Range: 3.1085. Min Range: -3.1085

Max Act: 2.9509. Min Act: -0.0000

Data Index: 1477048 (Python Code)

Max Activating Token Index: 340

Text #7

Max Range: 3.1085. Min Range: -3.1085

Max Act: 2.5354. Min Act: -0.0000

Data Index: 1469114 (Python Code)

Max Activating Token Index: 652

Text #8

Max Range: 3.1085. Min Range: -3.1085

Max Act: 3.1075. Min Act: -0.0000

Data Index: 1486204 (Python Code)

Max Activating Token Index: 695

Text #9

Max Range: 3.1085. Min Range: -3.1085

Max Act: 2.7674. Min Act: -0.0000

Data Index: 1513128 (Python Code)

Max Activating Token Index: 124

Text #10

Max Range: 3.1085. Min Range: -3.1085

Max Act: 2.8804. Min Act: -0.0000

Data Index: 1543639 (Python Code)

Max Activating Token Index: 676

Text #11

Max Range: 3.1085. Min Range: -3.1085

Max Act: 2.7004. Min Act: -0.0000

Data Index: 1489706 (Python Code)

Max Activating Token Index: 488

Text #12

Max Range: 3.1085. Min Range: -3.1085

Max Act: 2.5324. Min Act: -0.0000

Data Index: 1595325 (Python Code)

Max Activating Token Index: 53

Text #13

Max Range: 3.1085. Min Range: -3.1085

Max Act: 2.6762. Min Act: -0.0000

Data Index: 1392618 (Python Code)

Max Activating Token Index: 454

Text #14

Max Range: 3.1085. Min Range: -3.1085

Max Act: 2.5133. Min Act: -0.0000

Data Index: 1375390 (Python Code)

Max Activating Token Index: 665

Text #15

Max Range: 3.1085. Min Range: -3.1085

Max Act: 2.5938. Min Act: -0.0000

Data Index: 1522395 (Python Code)

Max Activating Token Index: 546

Text #16

Max Range: 3.1085. Min Range: -3.1085

Max Act: 2.5470. Min Act: -0.0000

Data Index: 1443957 (Python Code)

Max Activating Token Index: 184

Text #17

Max Range: 3.1085. Min Range: -3.1085

Max Act: 2.5249. Min Act: -0.0000

Data Index: 1406640 (Python Code)

Max Activating Token Index: 304

Text #18

Max Range: 3.1085. Min Range: -3.1085

Max Act: 2.5129. Min Act: -0.0000

Data Index: 1629646 (Python Code)

Max Activating Token Index: 645

Text #19

Max Range: 3.1085. Min Range: -3.1085

Max Act: 2.3947. Min Act: -0.0000

Data Index: 1466641 (Python Code)

Max Activating Token Index: 931