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

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

Neuron 5471 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0717. Min Range: -1.0717

Max Act: 1.0717. Min Act: -0.0001

Data Index: 386955 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1477951 (Python Code)

Max Activating Token Index: 710

Text #2

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1507809 (Python Code)

Max Activating Token Index: 823

Text #3

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8749. Min Act: -0.0000

Data Index: 1435498 (Python Code)

Max Activating Token Index: 366

Text #4

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8647. Min Act: -0.0000

Data Index: 1536964 (Python Code)

Max Activating Token Index: 726

Text #5

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.7968. Min Act: -0.0000

Data Index: 560854 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8357. Min Act: -0.0001

Data Index: 348865 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8529. Min Act: -0.0001

Data Index: 1141558 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8235. Min Act: -0.0000

Data Index: 243080 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8146. Min Act: -0.0001

Data Index: 673588 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.7749. Min Act: -0.0001

Data Index: 754976 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.7925. Min Act: -0.0001

Data Index: 389737 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.7865. Min Act: -0.0000

Data Index: 1150795 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.8256. Min Act: -0.0000

Data Index: 1341450 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.7806. Min Act: -0.0000

Data Index: 1007174 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.7296. Min Act: -0.0001

Data Index: 866079 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.7365. Min Act: -0.0001

Data Index: 606006 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.7570. Min Act: -0.0000

Data Index: 1431531 (Python Code)

Max Activating Token Index: 460

Text #18

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.7829. Min Act: -0.0000

Data Index: 836187 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 1.0717. Min Range: -1.0717

Max Act: 0.7469. Min Act: -0.0000

Data Index: 1103092 (C4 (Web Text))

Max Activating Token Index: 1012