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

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

Neuron 304 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: 0.2199. Min Range: -0.2199

Max Act: 0.2147. Min Act: -0.0001

Data Index: 540444 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1155172 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.2199. Min Act: -0.0000

Data Index: 695530 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.2036. Min Act: -0.0001

Data Index: 1611710 (Python Code)

Max Activating Token Index: 524

Text #4

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1918. Min Act: -0.0001

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1908. Min Act: -0.0000

Data Index: 593230 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1913. Min Act: -0.0000

Data Index: 1597146 (Python Code)

Max Activating Token Index: 86

Text #7

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1685. Min Act: -0.0000

Data Index: 1300628 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1624. Min Act: -0.0000

Data Index: 1415308 (Python Code)

Max Activating Token Index: 292

Text #9

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1613. Min Act: -0.0001

Data Index: 1237803 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1639. Min Act: -0.0000

Data Index: 626598 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1609. Min Act: -0.0000

Data Index: 1218983 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1560. Min Act: -0.0000

Data Index: 630715 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1582. Min Act: -0.0000

Data Index: 1460186 (Python Code)

Max Activating Token Index: 832

Text #14

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1575. Min Act: -0.0001

Data Index: 1483672 (Python Code)

Max Activating Token Index: 894

Text #15

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1581. Min Act: -0.0001

Data Index: 1183756 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1557. Min Act: -0.0000

Data Index: 1011380 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1436. Min Act: -0.0000

Data Index: 1244581 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1422. Min Act: -0.0000

Data Index: 225713 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1390. Min Act: -0.0000

Data Index: 757377 (C4 (Web Text))

Max Activating Token Index: 719