Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4354 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.9996. Min Act: -0.0000

Data Index: 1155156 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7845. Min Act: -0.0000

Data Index: 1047729 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6994. Min Act: -0.0000

Data Index: 118331 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6303. Min Act: -0.0000

Data Index: 1047474 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6074. Min Act: -0.0000

Data Index: 1037987 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.5397. Min Act: -0.0000

Data Index: 898693 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.5276. Min Act: -0.0000

Data Index: 677650 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.5371. Min Act: -0.0000

Data Index: 332230 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.5481. Min Act: -0.0000

Data Index: 759816 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.5152. Min Act: -0.0000

Data Index: 497469 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.5322. Min Act: -0.0000

Data Index: 743272 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.5093. Min Act: -0.0000

Data Index: 1251302 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1325334 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.4883. Min Act: -0.0000

Data Index: 1057809 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.4567. Min Act: -0.0000

Data Index: 623428 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.4916. Min Act: -0.0000

Data Index: 67527 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.4766. Min Act: -0.0000

Data Index: 992973 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.4592. Min Act: -0.0000

Data Index: 30894 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.4387. Min Act: -0.0000

Data Index: 1256196 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.4091. Min Act: -0.0000

Data Index: 381284 (C4 (Web Text))

Max Activating Token Index: 503