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

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

Neuron 1769 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1237. Min Act: -0.0001

Data Index: 1156115 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1170. Min Act: -0.0001

Data Index: 418565 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1202. Min Act: -0.0001

Data Index: 941672 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1111. Min Act: -0.0001

Data Index: 892115 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1147. Min Act: -0.0001

Data Index: 934671 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1055. Min Act: -0.0001

Data Index: 1338241 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1088. Min Act: -0.0001

Data Index: 302211 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1091. Min Act: -0.0001

Data Index: 626900 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1074. Min Act: -0.0001

Data Index: 845282 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1102. Min Act: -0.0001

Data Index: 120830 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1059. Min Act: -0.0001

Data Index: 540200 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1301590 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1241291 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1022. Min Act: -0.0001

Data Index: 776693 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0985. Min Act: -0.0001

Data Index: 861186 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0972. Min Act: -0.0001

Data Index: 634103 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0997. Min Act: -0.0001

Data Index: 159654 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1026. Min Act: -0.0001

Data Index: 1147674 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0946. Min Act: -0.0001

Data Index: 333628 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0885. Min Act: -0.0001

Data Index: 1295853 (C4 (Web Text))

Max Activating Token Index: 660