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

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

Neuron 4256 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.7625. Min Act: -0.0000

Data Index: 1159098 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.7326. Min Act: -0.0000

Data Index: 293821 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.5604. Min Act: -0.0000

Data Index: 366294 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.4551. Min Act: -0.0000

Data Index: 136904 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.4171. Min Act: -0.0000

Data Index: 119087 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.5619. Min Act: -0.0000

Data Index: 598698 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.5487. Min Act: -0.0000

Data Index: 1152168 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.3609. Min Act: -0.0000

Data Index: 523741 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.0274. Min Act: -0.0000

Data Index: 621679 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.3245. Min Act: -0.0000

Data Index: 1040861 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.2951. Min Act: -0.0000

Data Index: 1162517 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.2262. Min Act: -0.0000

Data Index: 1318704 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.1960. Min Act: -0.0000

Data Index: 646710 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.1979. Min Act: -0.0000

Data Index: 1093579 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.0445. Min Act: -0.0000

Data Index: 712924 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.1600. Min Act: -0.0000

Data Index: 461267 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.0020. Min Act: -0.0000

Data Index: 1213152 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.1476. Min Act: -0.0000

Data Index: 798660 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.1259. Min Act: -0.0000

Data Index: 720056 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 3.7625. Min Range: -3.7625

Max Act: 3.1202. Min Act: -0.0000

Data Index: 485983 (C4 (Web Text))

Max Activating Token Index: 859