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

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

Neuron 2953 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: 0.2676. Min Range: -0.2676

Max Act: 0.2660. Min Act: -0.0001

Data Index: 958191 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.2676. Min Act: -0.0001

Data Index: 1277629 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.2334. Min Act: -0.0001

Data Index: 262964 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.2277. Min Act: -0.0001

Data Index: 1344127 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.2163. Min Act: -0.0001

Data Index: 1022429 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.2168. Min Act: -0.0001

Data Index: 917751 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.2051. Min Act: -0.0001

Data Index: 835012 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.2112. Min Act: -0.0001

Data Index: 1198166 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.2149. Min Act: -0.0001

Data Index: 1165568 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.2042. Min Act: -0.0001

Data Index: 42623 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.2083. Min Act: -0.0001

Data Index: 548393 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.2113. Min Act: -0.0001

Data Index: 1176434 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1905. Min Act: -0.0001

Data Index: 860253 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1802. Min Act: -0.0001

Data Index: 798739 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1892. Min Act: -0.0001

Data Index: 181137 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1952. Min Act: -0.0001

Data Index: 686869 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1787. Min Act: -0.0001

Data Index: 897728 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1839. Min Act: -0.0001

Data Index: 706549 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1835. Min Act: -0.0001

Data Index: 18989 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1805. Min Act: -0.0001

Data Index: 1105671 (C4 (Web Text))

Max Activating Token Index: 294