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

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

Neuron 713 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1462. Min Act: -0.0003

Data Index: 322097 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1221. Min Act: -0.0003

Data Index: 1314963 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1351. Min Act: -0.0003

Data Index: 1309373 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1242. Min Act: -0.0003

Data Index: 674929 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1067. Min Act: -0.0003

Data Index: 1177311 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1180. Min Act: -0.0003

Data Index: 425440 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1124. Min Act: -0.0003

Data Index: 1083479 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1075. Min Act: -0.0003

Data Index: 975935 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1026. Min Act: -0.0003

Data Index: 735116 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1009. Min Act: -0.0003

Data Index: 627798 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1094. Min Act: -0.0003

Data Index: 1310908 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1078. Min Act: -0.0003

Data Index: 83174 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0988. Min Act: -0.0003

Data Index: 906322 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1012. Min Act: -0.0003

Data Index: 754759 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0968. Min Act: -0.0003

Data Index: 504871 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0827. Min Act: -0.0003

Data Index: 1271459 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1032. Min Act: -0.0003

Data Index: 779719 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0808. Min Act: -0.0003

Data Index: 593139 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0943. Min Act: -0.0003

Data Index: 202617 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0839. Min Act: -0.0003

Data Index: 161648 (C4 (Web Text))

Max Activating Token Index: 810