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

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

Neuron 3911 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0272. Min Range: -1.0272

Max Act: 1.0272. Min Act: -0.0002

Data Index: 1403859 (Python Code)

Max Activating Token Index: 892

Text #1

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8493. Min Act: -0.0002

Data Index: 1377922 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7971. Min Act: -0.0002

Data Index: 1612649 (Python Code)

Max Activating Token Index: 61

Text #3

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7978. Min Act: -0.0002

Data Index: 1557854 (Python Code)

Max Activating Token Index: 915

Text #4

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7943. Min Act: -0.0002

Data Index: 1644943 (Python Code)

Max Activating Token Index: 50

Text #5

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8475. Min Act: -0.0002

Data Index: 1446250 (Python Code)

Max Activating Token Index: 241

Text #6

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7747. Min Act: -0.0002

Data Index: 1478524 (Python Code)

Max Activating Token Index: 937

Text #7

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.6889. Min Act: -0.0002

Data Index: 1610272 (Python Code)

Max Activating Token Index: 754

Text #8

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7512. Min Act: -0.0002

Data Index: 1628983 (Python Code)

Max Activating Token Index: 771

Text #9

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7700. Min Act: -0.0002

Data Index: 1572616 (Python Code)

Max Activating Token Index: 521

Text #10

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7538. Min Act: -0.0002

Data Index: 1630466 (Python Code)

Max Activating Token Index: 570

Text #11

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7415. Min Act: -0.0002

Data Index: 1448971 (Python Code)

Max Activating Token Index: 926

Text #12

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7401. Min Act: -0.0002

Data Index: 1582301 (Python Code)

Max Activating Token Index: 611

Text #13

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7225. Min Act: -0.0002

Data Index: 1367019 (Python Code)

Max Activating Token Index: 985

Text #14

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.6809. Min Act: -0.0002

Data Index: 1478663 (Python Code)

Max Activating Token Index: 697

Text #15

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7081. Min Act: -0.0002

Data Index: 1495874 (Python Code)

Max Activating Token Index: 240

Text #16

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.6828. Min Act: -0.0002

Data Index: 1649278 (Python Code)

Max Activating Token Index: 183

Text #17

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.6832. Min Act: -0.0002

Data Index: 1504747 (Python Code)

Max Activating Token Index: 1003

Text #18

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7413. Min Act: -0.0002

Data Index: 1432225 (Python Code)

Max Activating Token Index: 929

Text #19

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7152. Min Act: -0.0002

Data Index: 1502769 (Python Code)

Max Activating Token Index: 956