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

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

Neuron 473 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: 0.1422. Min Range: -0.1422

Max Act: 0.1422. Min Act: -0.0000

Data Index: 793682 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1390. Min Act: -0.0000

Data Index: 276786 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1267. Min Act: -0.0000

Data Index: 916595 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1209. Min Act: -0.0000

Data Index: 103816 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1214. Min Act: -0.0000

Data Index: 247857 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1208. Min Act: -0.0000

Data Index: 1115093 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1115. Min Act: -0.0000

Data Index: 872071 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1187. Min Act: -0.0001

Data Index: 44027 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1089. Min Act: -0.0000

Data Index: 262612 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1098. Min Act: -0.0000

Data Index: 1215597 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1105. Min Act: -0.0001

Data Index: 403775 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1086. Min Act: -0.0001

Data Index: 905974 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1056. Min Act: -0.0000

Data Index: 876955 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0946. Min Act: -0.0001

Data Index: 944093 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1050. Min Act: -0.0001

Data Index: 664322 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0998. Min Act: -0.0000

Data Index: 1201684 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1002. Min Act: -0.0001

Data Index: 1355886 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1003. Min Act: -0.0001

Data Index: 301057 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0968. Min Act: -0.0000

Data Index: 574261 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0975. Min Act: -0.0000

Data Index: 207551 (C4 (Web Text))

Max Activating Token Index: 667