Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 808 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1558. Min Act: -0.0000

Data Index: 864705 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1263. Min Act: -0.0001

Data Index: 480339 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1188. Min Act: -0.0000

Data Index: 344389 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1208. Min Act: -0.0001

Data Index: 954402 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1115. Min Act: -0.0000

Data Index: 820158 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1078. Min Act: -0.0001

Data Index: 684294 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1346796 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1026. Min Act: -0.0000

Data Index: 863307 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0975. Min Act: -0.0001

Data Index: 1228194 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1040. Min Act: -0.0000

Data Index: 633400 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1029. Min Act: -0.0001

Data Index: 55912 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1031. Min Act: -0.0001

Data Index: 408955 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1063. Min Act: -0.0000

Data Index: 87600 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0978. Min Act: -0.0001

Data Index: 428710 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1018. Min Act: -0.0000

Data Index: 968651 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0942. Min Act: -0.0000

Data Index: 516500 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0971. Min Act: -0.0000

Data Index: 873943 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1262165 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0959. Min Act: -0.0000

Data Index: 200211 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1106617 (C4 (Web Text))

Max Activating Token Index: 351