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

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

Neuron 1350 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1320. Min Act: -0.0006

Data Index: 23285 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1322. Min Act: -0.0006

Data Index: 1252759 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1105. Min Act: -0.0006

Data Index: 789440 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1105. Min Act: -0.0006

Data Index: 263854 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1080. Min Act: -0.0006

Data Index: 230153 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1097. Min Act: -0.0006

Data Index: 637490 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1053. Min Act: -0.0006

Data Index: 238561 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0996. Min Act: -0.0006

Data Index: 993653 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1076. Min Act: -0.0006

Data Index: 857813 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1061. Min Act: -0.0006

Data Index: 1256640 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1045. Min Act: -0.0006

Data Index: 710326 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1042. Min Act: -0.0006

Data Index: 972733 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0953. Min Act: -0.0006

Data Index: 1229905 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1013. Min Act: -0.0006

Data Index: 732905 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1010. Min Act: -0.0006

Data Index: 1151575 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0934. Min Act: -0.0006

Data Index: 17140 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0902. Min Act: -0.0006

Data Index: 362059 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0959. Min Act: -0.0006

Data Index: 419538 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0915. Min Act: -0.0006

Data Index: 1347952 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0949. Min Act: -0.0006

Data Index: 212120 (C4 (Web Text))

Max Activating Token Index: 345