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

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

Neuron 1172 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: 0.9814. Min Range: -0.9814

Max Act: 0.9814. Min Act: -0.0000

Data Index: 459169 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.8845. Min Act: -0.0000

Data Index: 23386 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.8218. Min Act: -0.0000

Data Index: 394236 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.8154. Min Act: -0.0000

Data Index: 125906 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.7789. Min Act: -0.0000

Data Index: 1168274 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.8256. Min Act: -0.0000

Data Index: 920469 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.8215. Min Act: -0.0000

Data Index: 1225678 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.7943. Min Act: -0.0000

Data Index: 490806 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.7201. Min Act: -0.0000

Data Index: 893850 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.7845. Min Act: -0.0000

Data Index: 825441 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.7438. Min Act: -0.0000

Data Index: 56751 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.7643. Min Act: -0.0000

Data Index: 1317966 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.7636. Min Act: -0.0000

Data Index: 206335 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.6590. Min Act: -0.0000

Data Index: 556016 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.6825. Min Act: -0.0000

Data Index: 281922 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.7523. Min Act: -0.0000

Data Index: 564125 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.6989. Min Act: -0.0000

Data Index: 493971 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.6762. Min Act: -0.0000

Data Index: 949513 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.6674. Min Act: -0.0000

Data Index: 765810 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.7058. Min Act: -0.0000

Data Index: 239463 (C4 (Web Text))

Max Activating Token Index: 811