Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2172 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.5780. Min Act: -0.0000

Data Index: 412597 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.2643. Min Act: -0.0000

Data Index: 924732 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.3117. Min Act: -0.0000

Data Index: 624364 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.1976. Min Act: -0.0000

Data Index: 1275886 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.0679. Min Act: -0.0000

Data Index: 791140 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.1130. Min Act: -0.0000

Data Index: 988533 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 1.5780. Min Range: -1.5780

Max Act: 0.8746. Min Act: -0.0000

Data Index: 621720 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 1.5780. Min Range: -1.5780

Max Act: 0.7378. Min Act: -0.0000

Data Index: 1230308 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 1.5780. Min Range: -1.5780

Max Act: 0.8508. Min Act: -0.0000

Data Index: 724465 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 1.5780. Min Range: -1.5780

Max Act: 0.8093. Min Act: -0.0000

Data Index: 867093 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 1.5780. Min Range: -1.5780

Max Act: 0.7981. Min Act: -0.0000

Data Index: 1072183 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 1.5780. Min Range: -1.5780

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1526714 (Python Code)

Max Activating Token Index: 185

Text #12

Max Range: 1.5780. Min Range: -1.5780

Max Act: 0.8409. Min Act: -0.0000

Data Index: 1477073 (Python Code)

Max Activating Token Index: 606

Text #13

Max Range: 1.5780. Min Range: -1.5780

Max Act: 0.8918. Min Act: -0.0000

Data Index: 1316595 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 1.5780. Min Range: -1.5780

Max Act: 0.7442. Min Act: -0.0000

Data Index: 104556 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 1.5780. Min Range: -1.5780

Max Act: 0.6803. Min Act: -0.0000

Data Index: 240495 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 1.5780. Min Range: -1.5780

Max Act: 0.7609. Min Act: -0.0000

Data Index: 295583 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 1.5780. Min Range: -1.5780

Max Act: 0.7484. Min Act: -0.0000

Data Index: 95885 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 1.5780. Min Range: -1.5780

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1604245 (Python Code)

Max Activating Token Index: 243

Text #19

Max Range: 1.5780. Min Range: -1.5780

Max Act: 0.7845. Min Act: -0.0000

Data Index: 716082 (C4 (Web Text))

Max Activating Token Index: 391