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

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

Neuron 2845 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: 0.2306. Min Range: -0.2306

Max Act: 0.2306. Min Act: -0.0001

Data Index: 1626456 (Python Code)

Max Activating Token Index: 270

Text #1

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1991. Min Act: -0.0001

Data Index: 1600835 (Python Code)

Max Activating Token Index: 679

Text #2

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1778. Min Act: -0.0001

Data Index: 325593 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1792. Min Act: -0.0001

Data Index: 783432 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1560. Min Act: -0.0001

Data Index: 930894 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1553. Min Act: -0.0001

Data Index: 1378003 (Python Code)

Max Activating Token Index: 850

Text #6

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1624. Min Act: -0.0001

Data Index: 153934 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1420. Min Act: -0.0001

Data Index: 1428440 (Python Code)

Max Activating Token Index: 217

Text #8

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1556. Min Act: -0.0001

Data Index: 1505227 (Python Code)

Max Activating Token Index: 469

Text #9

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1574. Min Act: -0.0001

Data Index: 367306 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1569. Min Act: -0.0001

Data Index: 1646304 (Python Code)

Max Activating Token Index: 809

Text #11

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1416191 (Python Code)

Max Activating Token Index: 318

Text #12

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1550. Min Act: -0.0001

Data Index: 1490539 (Python Code)

Max Activating Token Index: 678

Text #13

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1567. Min Act: -0.0000

Data Index: 1549381 (Python Code)

Max Activating Token Index: 935

Text #14

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1450. Min Act: -0.0000

Data Index: 1470955 (Python Code)

Max Activating Token Index: 369

Text #15

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1547. Min Act: -0.0001

Data Index: 1371497 (Python Code)

Max Activating Token Index: 578

Text #16

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1476. Min Act: -0.0001

Data Index: 1629855 (Python Code)

Max Activating Token Index: 983

Text #17

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1479. Min Act: -0.0001

Data Index: 1629780 (Python Code)

Max Activating Token Index: 911

Text #18

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1435. Min Act: -0.0001

Data Index: 639759 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1523. Min Act: -0.0001

Data Index: 1516769 (Python Code)

Max Activating Token Index: 364