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

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

Neuron 1358 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1353. Min Act: -0.0001

Data Index: 1280880 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1231. Min Act: -0.0001

Data Index: 195246 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1286. Min Act: -0.0001

Data Index: 813634 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1162. Min Act: -0.0001

Data Index: 1170570 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1114. Min Act: -0.0001

Data Index: 648354 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1116. Min Act: -0.0001

Data Index: 1055465 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1119. Min Act: -0.0001

Data Index: 862020 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1011. Min Act: -0.0001

Data Index: 168664 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1119326 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1294481 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1062. Min Act: -0.0001

Data Index: 401147 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1229517 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1005. Min Act: -0.0001

Data Index: 942136 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1040. Min Act: -0.0001

Data Index: 455183 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1309827 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0979. Min Act: -0.0001

Data Index: 797363 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1004. Min Act: -0.0001

Data Index: 644159 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1046. Min Act: -0.0001

Data Index: 51804 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1037. Min Act: -0.0001

Data Index: 587875 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0996. Min Act: -0.0001

Data Index: 384254 (C4 (Web Text))

Max Activating Token Index: 854