Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4092 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1655. Min Act: -0.0001

Data Index: 1332287 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1451. Min Act: -0.0001

Data Index: 782763 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1481. Min Act: -0.0001

Data Index: 622509 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1296. Min Act: -0.0001

Data Index: 385096 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1164. Min Act: -0.0001

Data Index: 6422 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1160. Min Act: -0.0001

Data Index: 532843 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1196. Min Act: -0.0001

Data Index: 274568 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1130. Min Act: -0.0001

Data Index: 1243352 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1091. Min Act: -0.0001

Data Index: 1051942 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1144. Min Act: -0.0001

Data Index: 340214 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1056. Min Act: -0.0001

Data Index: 7119 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1096. Min Act: -0.0001

Data Index: 312575 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1078. Min Act: -0.0001

Data Index: 794161 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1061. Min Act: -0.0001

Data Index: 27010 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1058. Min Act: -0.0001

Data Index: 56546 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1013. Min Act: -0.0001

Data Index: 324308 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.0983. Min Act: -0.0001

Data Index: 359088 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1046. Min Act: -0.0001

Data Index: 813522 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.0998. Min Act: -0.0001

Data Index: 676691 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1040. Min Act: -0.0001

Data Index: 639610 (C4 (Web Text))

Max Activating Token Index: 487