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

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

Neuron 965 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: 0.2785. Min Range: -0.2785

Max Act: 0.2726. Min Act: -0.0001

Data Index: 489798 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2785. Min Act: -0.0001

Data Index: 1103798 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2623. Min Act: -0.0001

Data Index: 323998 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.1643. Min Act: -0.0001

Data Index: 1181714 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2433. Min Act: -0.0001

Data Index: 699980 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2224. Min Act: -0.0001

Data Index: 428154 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2286. Min Act: -0.0001

Data Index: 383807 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2120. Min Act: -0.0001

Data Index: 31609 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2353. Min Act: -0.0001

Data Index: 1082736 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2266. Min Act: -0.0001

Data Index: 85818 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2085. Min Act: -0.0001

Data Index: 381476 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2468. Min Act: -0.0001

Data Index: 1333800 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2127. Min Act: -0.0001

Data Index: 979566 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.1873. Min Act: -0.0001

Data Index: 981359 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2346. Min Act: -0.0001

Data Index: 1008305 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.1952. Min Act: -0.0001

Data Index: 1078083 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2140. Min Act: -0.0001

Data Index: 359235 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2162. Min Act: -0.0001

Data Index: 872130 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2129. Min Act: -0.0001

Data Index: 767077 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2148. Min Act: -0.0001

Data Index: 798979 (C4 (Web Text))

Max Activating Token Index: 965