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

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

Neuron 173 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0259. Min Range: -1.0259

Max Act: 1.0259. Min Act: -0.0000

Data Index: 1413309 (Python Code)

Max Activating Token Index: 868

Text #1

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.8832. Min Act: -0.0000

Data Index: 1452086 (Python Code)

Max Activating Token Index: 149

Text #2

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.8479. Min Act: -0.0000

Data Index: 1546153 (Python Code)

Max Activating Token Index: 625

Text #3

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.8082. Min Act: -0.0000

Data Index: 1532204 (Python Code)

Max Activating Token Index: 853

Text #4

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.7344. Min Act: -0.0000

Data Index: 1399054 (Python Code)

Max Activating Token Index: 301

Text #5

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.7976. Min Act: -0.0000

Data Index: 1397193 (Python Code)

Max Activating Token Index: 987

Text #6

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.8000. Min Act: -0.0000

Data Index: 1494718 (Python Code)

Max Activating Token Index: 543

Text #7

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.7227. Min Act: -0.0000

Data Index: 1650432 (Python Code)

Max Activating Token Index: 185

Text #8

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.7428. Min Act: -0.0000

Data Index: 1570892 (Python Code)

Max Activating Token Index: 829

Text #9

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1496792 (Python Code)

Max Activating Token Index: 61

Text #10

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1431607 (Python Code)

Max Activating Token Index: 642

Text #11

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1524801 (Python Code)

Max Activating Token Index: 71

Text #12

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.7693. Min Act: -0.0000

Data Index: 1520223 (Python Code)

Max Activating Token Index: 157

Text #13

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.7131. Min Act: -0.0000

Data Index: 1414022 (Python Code)

Max Activating Token Index: 348

Text #14

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.7212. Min Act: -0.0000

Data Index: 1478614 (Python Code)

Max Activating Token Index: 218

Text #15

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.6794. Min Act: -0.0000

Data Index: 1375961 (Python Code)

Max Activating Token Index: 104

Text #16

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1445536 (Python Code)

Max Activating Token Index: 428

Text #17

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1463089 (Python Code)

Max Activating Token Index: 481

Text #18

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.7344. Min Act: -0.0000

Data Index: 1575595 (Python Code)

Max Activating Token Index: 653

Text #19

Max Range: 1.0259. Min Range: -1.0259

Max Act: 0.6616. Min Act: -0.0000

Data Index: 1509377 (Python Code)

Max Activating Token Index: 744