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

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

Neuron 1632 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.5717. Min Act: -0.0001

Data Index: 988635 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.5216. Min Act: -0.0001

Data Index: 787174 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.5107. Min Act: -0.0001

Data Index: 364767 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4662. Min Act: -0.0001

Data Index: 1313272 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4652. Min Act: -0.0001

Data Index: 882508 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4926. Min Act: -0.0001

Data Index: 271434 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4784. Min Act: -0.0001

Data Index: 217063 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4768. Min Act: -0.0001

Data Index: 126124 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4570. Min Act: -0.0001

Data Index: 389638 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4617. Min Act: -0.0001

Data Index: 1188205 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4421. Min Act: -0.0001

Data Index: 691793 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4455. Min Act: -0.0001

Data Index: 224868 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4320. Min Act: -0.0001

Data Index: 62096 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4736. Min Act: -0.0001

Data Index: 957653 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4229. Min Act: -0.0001

Data Index: 1123587 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4294. Min Act: -0.0001

Data Index: 586937 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4138. Min Act: -0.0001

Data Index: 706824 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4237. Min Act: -0.0001

Data Index: 142570 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.3800. Min Act: -0.0001

Data Index: 601895 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4262. Min Act: -0.0001

Data Index: 445963 (C4 (Web Text))

Max Activating Token Index: 250