Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1827 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1169. Min Act: -0.0003

Data Index: 1219837 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1121. Min Act: -0.0003

Data Index: 1075016 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1133. Min Act: -0.0003

Data Index: 1290655 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1054. Min Act: -0.0003

Data Index: 1124247 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1039. Min Act: -0.0003

Data Index: 760629 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1053. Min Act: -0.0003

Data Index: 61768 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1040. Min Act: -0.0004

Data Index: 42373 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1026. Min Act: -0.0003

Data Index: 791894 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1018. Min Act: -0.0003

Data Index: 611641 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1002. Min Act: -0.0003

Data Index: 109220 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0931. Min Act: -0.0003

Data Index: 120829 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0997. Min Act: -0.0003

Data Index: 869212 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0957. Min Act: -0.0004

Data Index: 155033 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0926. Min Act: -0.0003

Data Index: 698922 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0962. Min Act: -0.0004

Data Index: 1181204 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0961. Min Act: -0.0004

Data Index: 975941 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0953. Min Act: -0.0003

Data Index: 241256 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0917. Min Act: -0.0003

Data Index: 499232 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0923. Min Act: -0.0004

Data Index: 17687 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0930. Min Act: -0.0003

Data Index: 519131 (C4 (Web Text))

Max Activating Token Index: 313