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

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

Neuron 659 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: 1.4996. Min Range: -1.4996

Max Act: 1.4996. Min Act: -0.0000

Data Index: 382188 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 1.4996. Min Range: -1.4996

Max Act: 1.2968. Min Act: -0.0000

Data Index: 1023279 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 1.4996. Min Range: -1.4996

Max Act: 1.3225. Min Act: -0.0000

Data Index: 1626392 (Python Code)

Max Activating Token Index: 670

Text #3

Max Range: 1.4996. Min Range: -1.4996

Max Act: 1.4078. Min Act: -0.0000

Data Index: 892124 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 1.4996. Min Range: -1.4996

Max Act: 1.0399. Min Act: -0.0000

Data Index: 518338 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 1.4996. Min Range: -1.4996

Max Act: 1.0673. Min Act: -0.0000

Data Index: 1437683 (Python Code)

Max Activating Token Index: 997

Text #6

Max Range: 1.4996. Min Range: -1.4996

Max Act: 1.0550. Min Act: -0.0000

Data Index: 1485264 (Python Code)

Max Activating Token Index: 68

Text #7

Max Range: 1.4996. Min Range: -1.4996

Max Act: 1.0573. Min Act: -0.0000

Data Index: 1463533 (Python Code)

Max Activating Token Index: 882

Text #8

Max Range: 1.4996. Min Range: -1.4996

Max Act: 1.1310. Min Act: -0.0000

Data Index: 70138 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 1.4996. Min Range: -1.4996

Max Act: 0.9630. Min Act: -0.0000

Data Index: 291206 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 1.4996. Min Range: -1.4996

Max Act: 1.0355. Min Act: -0.0000

Data Index: 1456922 (Python Code)

Max Activating Token Index: 358

Text #11

Max Range: 1.4996. Min Range: -1.4996

Max Act: 1.0030. Min Act: -0.0000

Data Index: 1616901 (Python Code)

Max Activating Token Index: 688

Text #12

Max Range: 1.4996. Min Range: -1.4996

Max Act: 1.0612. Min Act: -0.0000

Data Index: 1563595 (Python Code)

Max Activating Token Index: 699

Text #13

Max Range: 1.4996. Min Range: -1.4996

Max Act: 1.0421. Min Act: -0.0000

Data Index: 1465502 (Python Code)

Max Activating Token Index: 979

Text #14

Max Range: 1.4996. Min Range: -1.4996

Max Act: 1.1094. Min Act: -0.0000

Data Index: 1395537 (Python Code)

Max Activating Token Index: 527

Text #15

Max Range: 1.4996. Min Range: -1.4996

Max Act: 0.9239. Min Act: -0.0000

Data Index: 1573857 (Python Code)

Max Activating Token Index: 938

Text #16

Max Range: 1.4996. Min Range: -1.4996

Max Act: 0.9570. Min Act: -0.0000

Data Index: 1256864 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 1.4996. Min Range: -1.4996

Max Act: 0.9913. Min Act: -0.0000

Data Index: 1036111 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 1.4996. Min Range: -1.4996

Max Act: 0.9735. Min Act: -0.0000

Data Index: 1446714 (Python Code)

Max Activating Token Index: 695

Text #19

Max Range: 1.4996. Min Range: -1.4996

Max Act: 1.0317. Min Act: -0.0000

Data Index: 1584861 (Python Code)

Max Activating Token Index: 988