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

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

Neuron 4720 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.4441. Min Act: -0.0000

Data Index: 1609794 (Python Code)

Max Activating Token Index: 125

Text #1

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2987. Min Act: -0.0000

Data Index: 1478741 (Python Code)

Max Activating Token Index: 826

Text #2

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.3487. Min Act: -0.0000

Data Index: 1588922 (Python Code)

Max Activating Token Index: 200

Text #3

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2823. Min Act: -0.0001

Data Index: 1550184 (Python Code)

Max Activating Token Index: 416

Text #4

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.3132. Min Act: -0.0000

Data Index: 1518863 (Python Code)

Max Activating Token Index: 453

Text #5

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2650. Min Act: -0.0000

Data Index: 1537376 (Python Code)

Max Activating Token Index: 812

Text #6

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2093. Min Act: -0.0000

Data Index: 1652077 (Python Code)

Max Activating Token Index: 815

Text #7

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.3154. Min Act: -0.0000

Data Index: 1515213 (Python Code)

Max Activating Token Index: 884

Text #8

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2622. Min Act: -0.0000

Data Index: 1534255 (Python Code)

Max Activating Token Index: 59

Text #9

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2175. Min Act: -0.0000

Data Index: 1537164 (Python Code)

Max Activating Token Index: 846

Text #10

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2189. Min Act: -0.0000

Data Index: 1446501 (Python Code)

Max Activating Token Index: 38

Text #11

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2047. Min Act: -0.0000

Data Index: 1425539 (Python Code)

Max Activating Token Index: 659

Text #12

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2322. Min Act: -0.0000

Data Index: 1500435 (Python Code)

Max Activating Token Index: 941

Text #13

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.1958. Min Act: -0.0000

Data Index: 1579622 (Python Code)

Max Activating Token Index: 556

Text #14

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2258. Min Act: -0.0000

Data Index: 1653260 (Python Code)

Max Activating Token Index: 430

Text #15

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2481. Min Act: -0.0001

Data Index: 1599758 (Python Code)

Max Activating Token Index: 952

Text #16

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2765. Min Act: -0.0001

Data Index: 1619523 (Python Code)

Max Activating Token Index: 293

Text #17

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.0684. Min Act: -0.0000

Data Index: 1622565 (Python Code)

Max Activating Token Index: 49

Text #18

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2454. Min Act: -0.0000

Data Index: 1487622 (Python Code)

Max Activating Token Index: 636

Text #19

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2166. Min Act: -0.0000

Data Index: 1557866 (Python Code)

Max Activating Token Index: 368