Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1845 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3748. Min Range: -0.3748

Max Act: 0.3748. Min Act: -0.0000

Data Index: 1397029 (Python Code)

Max Activating Token Index: 539

Text #1

Max Range: 0.3748. Min Range: -0.3748

Max Act: 0.3051. Min Act: -0.0000

Data Index: 1419009 (Python Code)

Max Activating Token Index: 984

Text #2

Max Range: 0.3748. Min Range: -0.3748

Max Act: 0.2839. Min Act: -0.0001

Data Index: 1528735 (Python Code)

Max Activating Token Index: 167

Text #3

Max Range: 0.3748. Min Range: -0.3748

Max Act: 0.2854. Min Act: -0.0001

Data Index: 1386988 (Python Code)

Max Activating Token Index: 343

Text #4

Max Range: 0.3748. Min Range: -0.3748

Max Act: 0.2747. Min Act: -0.0000

Data Index: 1442984 (Python Code)

Max Activating Token Index: 475

Text #5

Max Range: 0.3748. Min Range: -0.3748

Max Act: 0.2810. Min Act: -0.0001

Data Index: 1543551 (Python Code)

Max Activating Token Index: 264

Text #6

Max Range: 0.3748. Min Range: -0.3748

Max Act: 0.2788. Min Act: -0.0001

Data Index: 1549832 (Python Code)

Max Activating Token Index: 819

Text #7

Max Range: 0.3748. Min Range: -0.3748

Max Act: 0.2848. Min Act: -0.0001

Data Index: 1584712 (Python Code)

Max Activating Token Index: 886

Text #8

Max Range: 0.3748. Min Range: -0.3748

Max Act: 0.2742. Min Act: -0.0001

Data Index: 1435593 (Python Code)

Max Activating Token Index: 330

Text #9

Max Range: 0.3748. Min Range: -0.3748

Max Act: 0.2706. Min Act: -0.0000

Data Index: 1459488 (Python Code)

Max Activating Token Index: 122

Text #10

Max Range: 0.3748. Min Range: -0.3748

Max Act: 0.2587. Min Act: -0.0000

Data Index: 1595153 (Python Code)

Max Activating Token Index: 950

Text #11

Max Range: 0.3748. Min Range: -0.3748

Max Act: 0.2598. Min Act: -0.0001

Data Index: 1461946 (Python Code)

Max Activating Token Index: 910

Text #12

Max Range: 0.3748. Min Range: -0.3748

Max Act: 0.2525. Min Act: -0.0000

Data Index: 1633869 (Python Code)

Max Activating Token Index: 283

Text #13

Max Range: 0.3748. Min Range: -0.3748

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1584016 (Python Code)

Max Activating Token Index: 500

Text #14

Max Range: 0.3748. Min Range: -0.3748

Max Act: 0.2405. Min Act: -0.0001

Data Index: 1569463 (Python Code)

Max Activating Token Index: 326

Text #15

Max Range: 0.3748. Min Range: -0.3748

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1656330 (Python Code)

Max Activating Token Index: 993

Text #16

Max Range: 0.3748. Min Range: -0.3748

Max Act: 0.2442. Min Act: -0.0001

Data Index: 1492317 (Python Code)

Max Activating Token Index: 22

Text #17

Max Range: 0.3748. Min Range: -0.3748

Max Act: 0.2481. Min Act: -0.0000

Data Index: 1505838 (Python Code)

Max Activating Token Index: 427

Text #18

Max Range: 0.3748. Min Range: -0.3748

Max Act: 0.2511. Min Act: -0.0001

Data Index: 1651661 (Python Code)

Max Activating Token Index: 715

Text #19

Max Range: 0.3748. Min Range: -0.3748

Max Act: 0.2504. Min Act: -0.0000

Data Index: 1506774 (Python Code)

Max Activating Token Index: 139