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

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

Neuron 254 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1609. Min Range: -1.1609

Max Act: 1.1574. Min Act: -0.0000

Data Index: 858167 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 1.1609. Min Range: -1.1609

Max Act: 1.1609. Min Act: -0.0000

Data Index: 42759 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 1.1609. Min Range: -1.1609

Max Act: 1.0099. Min Act: -0.0000

Data Index: 95122 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 1.1609. Min Range: -1.1609

Max Act: 0.7817. Min Act: -0.0000

Data Index: 691090 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 1.1609. Min Range: -1.1609

Max Act: 0.7344. Min Act: -0.0000

Data Index: 679304 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 1.1609. Min Range: -1.1609

Max Act: 0.6542. Min Act: -0.0000

Data Index: 429652 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 1.1609. Min Range: -1.1609

Max Act: 0.7087. Min Act: -0.0000

Data Index: 1352092 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 1.1609. Min Range: -1.1609

Max Act: 0.6391. Min Act: -0.0000

Data Index: 604343 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 1.1609. Min Range: -1.1609

Max Act: 0.6951. Min Act: -0.0000

Data Index: 85107 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 1.1609. Min Range: -1.1609

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1126076 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 1.1609. Min Range: -1.1609

Max Act: 0.6368. Min Act: -0.0000

Data Index: 166236 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 1.1609. Min Range: -1.1609

Max Act: 0.6114. Min Act: -0.0000

Data Index: 1225409 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 1.1609. Min Range: -1.1609

Max Act: 0.6262. Min Act: -0.0000

Data Index: 409770 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 1.1609. Min Range: -1.1609

Max Act: 0.5701. Min Act: -0.0000

Data Index: 188061 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 1.1609. Min Range: -1.1609

Max Act: 0.6056. Min Act: -0.0000

Data Index: 1323095 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 1.1609. Min Range: -1.1609

Max Act: 0.5723. Min Act: -0.0000

Data Index: 924172 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 1.1609. Min Range: -1.1609

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1160863 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 1.1609. Min Range: -1.1609

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1219189 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 1.1609. Min Range: -1.1609

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1270611 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 1.1609. Min Range: -1.1609

Max Act: 0.5264. Min Act: -0.0000

Data Index: 1356163 (C4 (Web Text))

Max Activating Token Index: 21