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

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

Neuron 4141 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.8128. Min Act: -0.0000

Data Index: 600027 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.8144. Min Act: -0.0000

Data Index: 1075263 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.7451. Min Act: -0.0000

Data Index: 901910 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.7800. Min Act: -0.0000

Data Index: 1155891 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.7157. Min Act: -0.0000

Data Index: 557940 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.7267. Min Act: -0.0000

Data Index: 960080 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6613. Min Act: -0.0000

Data Index: 25718 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.7226. Min Act: 0.0000

Data Index: 467988 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6993. Min Act: -0.0000

Data Index: 239497 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6599. Min Act: -0.0000

Data Index: 1201528 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.7477. Min Act: -0.0000

Data Index: 606668 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6786. Min Act: -0.0000

Data Index: 105258 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6662. Min Act: -0.0000

Data Index: 675068 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1017584 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6844. Min Act: -0.0000

Data Index: 1128572 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.7021. Min Act: -0.0000

Data Index: 862305 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6593. Min Act: -0.0000

Data Index: 707362 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6567. Min Act: -0.0000

Data Index: 436938 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6546. Min Act: -0.0000

Data Index: 845251 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6260. Min Act: -0.0000

Data Index: 449856 (C4 (Web Text))

Max Activating Token Index: 797