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

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

Neuron 997 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3799. Min Range: -1.3799

Max Act: 1.3799. Min Act: -0.0001

Data Index: 1364074 (Python Code)

Max Activating Token Index: 855

Text #1

Max Range: 1.3799. Min Range: -1.3799

Max Act: 0.9457. Min Act: -0.0001

Data Index: 1528683 (Python Code)

Max Activating Token Index: 772

Text #2

Max Range: 1.3799. Min Range: -1.3799

Max Act: 1.0484. Min Act: -0.0001

Data Index: 1509214 (Python Code)

Max Activating Token Index: 48

Text #3

Max Range: 1.3799. Min Range: -1.3799

Max Act: 1.1374. Min Act: -0.0001

Data Index: 1500884 (Python Code)

Max Activating Token Index: 541

Text #4

Max Range: 1.3799. Min Range: -1.3799

Max Act: 0.8743. Min Act: -0.0001

Data Index: 1480763 (Python Code)

Max Activating Token Index: 807

Text #5

Max Range: 1.3799. Min Range: -1.3799

Max Act: 1.0294. Min Act: -0.0001

Data Index: 1475704 (Python Code)

Max Activating Token Index: 201

Text #6

Max Range: 1.3799. Min Range: -1.3799

Max Act: 1.1858. Min Act: -0.0001

Data Index: 1470525 (Python Code)

Max Activating Token Index: 920

Text #7

Max Range: 1.3799. Min Range: -1.3799

Max Act: 1.1265. Min Act: -0.0001

Data Index: 1604383 (Python Code)

Max Activating Token Index: 528

Text #8

Max Range: 1.3799. Min Range: -1.3799

Max Act: 1.1492. Min Act: -0.0001

Data Index: 1413345 (Python Code)

Max Activating Token Index: 563

Text #9

Max Range: 1.3799. Min Range: -1.3799

Max Act: 1.0230. Min Act: -0.0001

Data Index: 1523143 (Python Code)

Max Activating Token Index: 924

Text #10

Max Range: 1.3799. Min Range: -1.3799

Max Act: 1.0423. Min Act: -0.0001

Data Index: 1514608 (Python Code)

Max Activating Token Index: 473

Text #11

Max Range: 1.3799. Min Range: -1.3799

Max Act: 1.0688. Min Act: -0.0001

Data Index: 1624876 (Python Code)

Max Activating Token Index: 432

Text #12

Max Range: 1.3799. Min Range: -1.3799

Max Act: 1.0352. Min Act: -0.0000

Data Index: 1437020 (Python Code)

Max Activating Token Index: 3

Text #13

Max Range: 1.3799. Min Range: -1.3799

Max Act: 1.0352. Min Act: -0.0001

Data Index: 1460083 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 1.3799. Min Range: -1.3799

Max Act: 1.0352. Min Act: -0.0001

Data Index: 1435996 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 1.3799. Min Range: -1.3799

Max Act: 1.0352. Min Act: -0.0001

Data Index: 1583262 (Python Code)

Max Activating Token Index: 3

Text #16

Max Range: 1.3799. Min Range: -1.3799

Max Act: 1.0352. Min Act: -0.0001

Data Index: 1366428 (Python Code)

Max Activating Token Index: 3

Text #17

Max Range: 1.3799. Min Range: -1.3799

Max Act: 1.0352. Min Act: -0.0001

Data Index: 1516651 (Python Code)

Max Activating Token Index: 3

Text #18

Max Range: 1.3799. Min Range: -1.3799

Max Act: 1.0352. Min Act: -0.0001

Data Index: 1498970 (Python Code)

Max Activating Token Index: 3

Text #19

Max Range: 1.3799. Min Range: -1.3799

Max Act: 1.0352. Min Act: -0.0001

Data Index: 1603964 (Python Code)

Max Activating Token Index: 3