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

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

Neuron 1380 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1178. Min Act: -0.0001

Data Index: 600307 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1141. Min Act: -0.0001

Data Index: 187488 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1136. Min Act: -0.0001

Data Index: 1247833 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1061. Min Act: -0.0001

Data Index: 1266448 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1060. Min Act: -0.0001

Data Index: 825067 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0977. Min Act: -0.0001

Data Index: 295088 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0988. Min Act: -0.0001

Data Index: 779049 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1020. Min Act: -0.0001

Data Index: 265512 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0976. Min Act: -0.0001

Data Index: 538731 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0990. Min Act: -0.0001

Data Index: 743858 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0980. Min Act: -0.0001

Data Index: 1292539 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0943. Min Act: -0.0001

Data Index: 898854 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0931. Min Act: -0.0001

Data Index: 1199095 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0960. Min Act: -0.0001

Data Index: 1289806 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0950. Min Act: -0.0001

Data Index: 900363 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0937. Min Act: -0.0001

Data Index: 496527 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0986. Min Act: -0.0001

Data Index: 530142 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0913. Min Act: -0.0001

Data Index: 668020 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0908. Min Act: -0.0001

Data Index: 327230 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0903. Min Act: -0.0001

Data Index: 1536701 (Python Code)

Max Activating Token Index: 591