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

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

Neuron 5558 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7945. Min Range: -1.7945

Max Act: 1.6727. Min Act: -0.0000

Data Index: 1217042 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 1.7945. Min Range: -1.7945

Max Act: 1.7945. Min Act: -0.0000

Data Index: 931161 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 1.7945. Min Range: -1.7945

Max Act: 1.5026. Min Act: -0.0000

Data Index: 629458 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 1.7945. Min Range: -1.7945

Max Act: 1.4005. Min Act: -0.0000

Data Index: 184807 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 1.7945. Min Range: -1.7945

Max Act: 1.4931. Min Act: -0.0000

Data Index: 1062675 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 1.7945. Min Range: -1.7945

Max Act: 1.3405. Min Act: -0.0000

Data Index: 741939 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 1.7945. Min Range: -1.7945

Max Act: 1.2618. Min Act: -0.0000

Data Index: 441771 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 1.7945. Min Range: -1.7945

Max Act: 1.4237. Min Act: -0.0000

Data Index: 1061510 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 1.7945. Min Range: -1.7945

Max Act: 1.4196. Min Act: -0.0000

Data Index: 1053453 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 1.7945. Min Range: -1.7945

Max Act: 1.2560. Min Act: -0.0000

Data Index: 883636 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 1.7945. Min Range: -1.7945

Max Act: 1.2754. Min Act: -0.0000

Data Index: 640965 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 1.7945. Min Range: -1.7945

Max Act: 1.2979. Min Act: -0.0000

Data Index: 1261645 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 1.7945. Min Range: -1.7945

Max Act: 1.3099. Min Act: -0.0000

Data Index: 108361 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 1.7945. Min Range: -1.7945

Max Act: 1.2947. Min Act: -0.0000

Data Index: 1192911 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 1.7945. Min Range: -1.7945

Max Act: 1.3445. Min Act: -0.0000

Data Index: 1200559 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 1.7945. Min Range: -1.7945

Max Act: 1.1294. Min Act: -0.0000

Data Index: 66420 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 1.7945. Min Range: -1.7945

Max Act: 1.1961. Min Act: -0.0000

Data Index: 1287056 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 1.7945. Min Range: -1.7945

Max Act: 1.1273. Min Act: -0.0000

Data Index: 1039076 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 1.7945. Min Range: -1.7945

Max Act: 1.1881. Min Act: -0.0000

Data Index: 684577 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 1.7945. Min Range: -1.7945

Max Act: 1.1200. Min Act: -0.0000

Data Index: 126138 (C4 (Web Text))

Max Activating Token Index: 464