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

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

Neuron 1271 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1387877 (Python Code)

Max Activating Token Index: 690

Text #1

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1492012 (Python Code)

Max Activating Token Index: 674

Text #2

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.6921. Min Act: -0.0000

Data Index: 1641516 (Python Code)

Max Activating Token Index: 582

Text #3

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.6597. Min Act: -0.0000

Data Index: 1406735 (Python Code)

Max Activating Token Index: 595

Text #4

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.6301. Min Act: -0.0000

Data Index: 1519868 (Python Code)

Max Activating Token Index: 454

Text #5

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.6587. Min Act: -0.0000

Data Index: 1388596 (Python Code)

Max Activating Token Index: 516

Text #6

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.6643. Min Act: -0.0000

Data Index: 1452492 (Python Code)

Max Activating Token Index: 766

Text #7

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.6262. Min Act: -0.0000

Data Index: 1377346 (Python Code)

Max Activating Token Index: 679

Text #8

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.6081. Min Act: -0.0000

Data Index: 1552334 (Python Code)

Max Activating Token Index: 88

Text #9

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1415956 (Python Code)

Max Activating Token Index: 674

Text #10

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1575772 (Python Code)

Max Activating Token Index: 614

Text #11

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1562018 (Python Code)

Max Activating Token Index: 906

Text #12

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1544247 (Python Code)

Max Activating Token Index: 809

Text #13

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.5312. Min Act: -0.0000

Data Index: 1655626 (Python Code)

Max Activating Token Index: 937

Text #14

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.5114. Min Act: -0.0000

Data Index: 1392803 (Python Code)

Max Activating Token Index: 346

Text #15

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1624744 (Python Code)

Max Activating Token Index: 749

Text #16

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1367309 (Python Code)

Max Activating Token Index: 727

Text #17

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.5782. Min Act: -0.0000

Data Index: 1641544 (Python Code)

Max Activating Token Index: 823

Text #18

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1478850 (Python Code)

Max Activating Token Index: 329

Text #19

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1606796 (Python Code)

Max Activating Token Index: 334