Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2807 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1811. Min Act: -0.0000

Data Index: 488074 (The Pile)

Max Activating Token Index: 924

Text #1

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1477. Min Act: -0.0000

Data Index: 421089 (The Pile)

Max Activating Token Index: 512

Text #2

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1505. Min Act: -0.0000

Data Index: 875751 (The Pile)

Max Activating Token Index: 690

Text #3

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1197. Min Act: -0.0000

Data Index: 1464656 (The Pile)

Max Activating Token Index: 793

Text #4

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1321. Min Act: -0.0000

Data Index: 1647400 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1805343 (The Pile)

Max Activating Token Index: 639

Text #6

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1313. Min Act: -0.0000

Data Index: 1115107 (The Pile)

Max Activating Token Index: 344

Text #7

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1310. Min Act: -0.0000

Data Index: 1524044 (The Pile)

Max Activating Token Index: 746

Text #8

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1166. Min Act: -0.0000

Data Index: 1025869 (The Pile)

Max Activating Token Index: 965

Text #9

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1736185 (The Pile)

Max Activating Token Index: 745

Text #10

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1128. Min Act: -0.0000

Data Index: 1084184 (The Pile)

Max Activating Token Index: 750

Text #11

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1075. Min Act: -0.0000

Data Index: 152001 (The Pile)

Max Activating Token Index: 908

Text #12

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1066. Min Act: -0.0000

Data Index: 266816 (The Pile)

Max Activating Token Index: 666

Text #13

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1630363 (The Pile)

Max Activating Token Index: 650

Text #14

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1081. Min Act: -0.0001

Data Index: 1391200 (The Pile)

Max Activating Token Index: 531

Text #15

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1024607 (The Pile)

Max Activating Token Index: 904

Text #16

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1329794 (The Pile)

Max Activating Token Index: 358

Text #17

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1022. Min Act: -0.0000

Data Index: 1425845 (The Pile)

Max Activating Token Index: 261

Text #18

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1048. Min Act: -0.0000

Data Index: 442632 (The Pile)

Max Activating Token Index: 162

Text #19

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1328250 (The Pile)

Max Activating Token Index: 103