Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4568 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0359. Min Range: -1.0359

Max Act: 1.0055. Min Act: -0.0001

Data Index: 1368651 (Python Code)

Max Activating Token Index: 783

Text #1

Max Range: 1.0359. Min Range: -1.0359

Max Act: 1.0054. Min Act: -0.0002

Data Index: 1656795 (Python Code)

Max Activating Token Index: 441

Text #2

Max Range: 1.0359. Min Range: -1.0359

Max Act: 1.0359. Min Act: -0.0002

Data Index: 1443731 (Python Code)

Max Activating Token Index: 683

Text #3

Max Range: 1.0359. Min Range: -1.0359

Max Act: 0.9615. Min Act: -0.0002

Data Index: 1503208 (Python Code)

Max Activating Token Index: 561

Text #4

Max Range: 1.0359. Min Range: -1.0359

Max Act: 0.9622. Min Act: -0.0002

Data Index: 1525281 (Python Code)

Max Activating Token Index: 521

Text #5

Max Range: 1.0359. Min Range: -1.0359

Max Act: 0.9784. Min Act: -0.0002

Data Index: 1467587 (Python Code)

Max Activating Token Index: 437

Text #6

Max Range: 1.0359. Min Range: -1.0359

Max Act: 0.9638. Min Act: -0.0002

Data Index: 1492666 (Python Code)

Max Activating Token Index: 625

Text #7

Max Range: 1.0359. Min Range: -1.0359

Max Act: 0.8472. Min Act: -0.0002

Data Index: 1648503 (Python Code)

Max Activating Token Index: 1000

Text #8

Max Range: 1.0359. Min Range: -1.0359

Max Act: 0.9401. Min Act: -0.0002

Data Index: 1604993 (Python Code)

Max Activating Token Index: 478

Text #9

Max Range: 1.0359. Min Range: -1.0359

Max Act: 0.7913. Min Act: -0.0001

Data Index: 1449175 (Python Code)

Max Activating Token Index: 217

Text #10

Max Range: 1.0359. Min Range: -1.0359

Max Act: 0.8786. Min Act: -0.0001

Data Index: 1590425 (Python Code)

Max Activating Token Index: 120

Text #11

Max Range: 1.0359. Min Range: -1.0359

Max Act: 0.8246. Min Act: -0.0001

Data Index: 1432623 (Python Code)

Max Activating Token Index: 971

Text #12

Max Range: 1.0359. Min Range: -1.0359

Max Act: 0.8038. Min Act: -0.0001

Data Index: 1420729 (Python Code)

Max Activating Token Index: 681

Text #13

Max Range: 1.0359. Min Range: -1.0359

Max Act: 0.7714. Min Act: -0.0001

Data Index: 1617813 (Python Code)

Max Activating Token Index: 421

Text #14

Max Range: 1.0359. Min Range: -1.0359

Max Act: 0.8291. Min Act: -0.0001

Data Index: 1647358 (Python Code)

Max Activating Token Index: 682

Text #15

Max Range: 1.0359. Min Range: -1.0359

Max Act: 0.8278. Min Act: -0.0001

Data Index: 1525168 (Python Code)

Max Activating Token Index: 664

Text #16

Max Range: 1.0359. Min Range: -1.0359

Max Act: 0.7854. Min Act: -0.0001

Data Index: 1569419 (Python Code)

Max Activating Token Index: 403

Text #17

Max Range: 1.0359. Min Range: -1.0359

Max Act: 0.7910. Min Act: -0.0001

Data Index: 1360868 (Python Code)

Max Activating Token Index: 418

Text #18

Max Range: 1.0359. Min Range: -1.0359

Max Act: 0.7909. Min Act: -0.0001

Data Index: 1418389 (Python Code)

Max Activating Token Index: 740

Text #19

Max Range: 1.0359. Min Range: -1.0359

Max Act: 0.7437. Min Act: -0.0001

Data Index: 1610836 (Python Code)

Max Activating Token Index: 116