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

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

Neuron 2479 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3706. Min Range: -2.3706

Max Act: 2.1361. Min Act: -0.0000

Data Index: 1439070 (Python Code)

Max Activating Token Index: 251

Text #1

Max Range: 2.3706. Min Range: -2.3706

Max Act: 2.2916. Min Act: -0.0000

Data Index: 1366212 (Python Code)

Max Activating Token Index: 1004

Text #2

Max Range: 2.3706. Min Range: -2.3706

Max Act: 2.1614. Min Act: -0.0000

Data Index: 1389650 (Python Code)

Max Activating Token Index: 409

Text #3

Max Range: 2.3706. Min Range: -2.3706

Max Act: 2.2569. Min Act: -0.0000

Data Index: 1394990 (Python Code)

Max Activating Token Index: 572

Text #4

Max Range: 2.3706. Min Range: -2.3706

Max Act: 2.3706. Min Act: -0.0000

Data Index: 1541120 (Python Code)

Max Activating Token Index: 252

Text #5

Max Range: 2.3706. Min Range: -2.3706

Max Act: 2.2610. Min Act: -0.0000

Data Index: 1398298 (Python Code)

Max Activating Token Index: 534

Text #6

Max Range: 2.3706. Min Range: -2.3706

Max Act: 2.2371. Min Act: -0.0000

Data Index: 1536382 (Python Code)

Max Activating Token Index: 608

Text #7

Max Range: 2.3706. Min Range: -2.3706

Max Act: 2.2448. Min Act: -0.0000

Data Index: 1399989 (Python Code)

Max Activating Token Index: 641

Text #8

Max Range: 2.3706. Min Range: -2.3706

Max Act: 2.2458. Min Act: -0.0000

Data Index: 1482863 (Python Code)

Max Activating Token Index: 767

Text #9

Max Range: 2.3706. Min Range: -2.3706

Max Act: 2.2410. Min Act: -0.0000

Data Index: 1373592 (Python Code)

Max Activating Token Index: 679

Text #10

Max Range: 2.3706. Min Range: -2.3706

Max Act: 2.2384. Min Act: -0.0000

Data Index: 1565660 (Python Code)

Max Activating Token Index: 728

Text #11

Max Range: 2.3706. Min Range: -2.3706

Max Act: 2.0748. Min Act: -0.0000

Data Index: 1460782 (Python Code)

Max Activating Token Index: 804

Text #12

Max Range: 2.3706. Min Range: -2.3706

Max Act: 2.1656. Min Act: -0.0000

Data Index: 1491739 (Python Code)

Max Activating Token Index: 1011

Text #13

Max Range: 2.3706. Min Range: -2.3706

Max Act: 2.1653. Min Act: -0.0000

Data Index: 1524633 (Python Code)

Max Activating Token Index: 376

Text #14

Max Range: 2.3706. Min Range: -2.3706

Max Act: 2.2955. Min Act: -0.0000

Data Index: 1469742 (Python Code)

Max Activating Token Index: 242

Text #15

Max Range: 2.3706. Min Range: -2.3706

Max Act: 2.1671. Min Act: -0.0000

Data Index: 1519316 (Python Code)

Max Activating Token Index: 201

Text #16

Max Range: 2.3706. Min Range: -2.3706

Max Act: 2.1613. Min Act: -0.0000

Data Index: 1430470 (Python Code)

Max Activating Token Index: 485

Text #17

Max Range: 2.3706. Min Range: -2.3706

Max Act: 2.2480. Min Act: -0.0000

Data Index: 1367807 (Python Code)

Max Activating Token Index: 269

Text #18

Max Range: 2.3706. Min Range: -2.3706

Max Act: 2.0208. Min Act: -0.0000

Data Index: 1540221 (Python Code)

Max Activating Token Index: 201

Text #19

Max Range: 2.3706. Min Range: -2.3706

Max Act: 2.0288. Min Act: -0.0000

Data Index: 1395833 (Python Code)

Max Activating Token Index: 488