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

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

Neuron 1885 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2509. Min Act: -0.0000

Data Index: 651679 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1250. Min Act: -0.0000

Data Index: 507910 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1202. Min Act: -0.0000

Data Index: 423620 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1198. Min Act: -0.0000

Data Index: 1316265 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1211. Min Act: -0.0000

Data Index: 945586 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1128. Min Act: -0.0000

Data Index: 1046998 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1120. Min Act: -0.0000

Data Index: 968497 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1133. Min Act: -0.0001

Data Index: 1129770 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1138. Min Act: -0.0000

Data Index: 238665 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1155. Min Act: 0.0000

Data Index: 348138 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1039. Min Act: -0.0000

Data Index: 1065690 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1016. Min Act: -0.0000

Data Index: 1318175 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1058. Min Act: -0.0001

Data Index: 881214 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1288214 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.0969. Min Act: -0.0000

Data Index: 870548 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.0974. Min Act: -0.0000

Data Index: 896397 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1042. Min Act: -0.0000

Data Index: 1089239 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1010. Min Act: -0.0000

Data Index: 967781 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1034. Min Act: -0.0000

Data Index: 622602 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.0928. Min Act: -0.0001

Data Index: 219120 (C4 (Web Text))

Max Activating Token Index: 559