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

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

Neuron 4586 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.3193. Min Act: -0.0000

Data Index: 1598841 (Python Code)

Max Activating Token Index: 452

Text #1

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.2474. Min Act: -0.0000

Data Index: 544176 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.1966. Min Act: -0.0000

Data Index: 981383 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.0514. Min Act: -0.0000

Data Index: 1554918 (Python Code)

Max Activating Token Index: 400

Text #4

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.0445. Min Act: -0.0000

Data Index: 1429777 (Python Code)

Max Activating Token Index: 37

Text #5

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9993. Min Act: -0.0000

Data Index: 379647 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9944. Min Act: -0.0000

Data Index: 1429798 (Python Code)

Max Activating Token Index: 384

Text #7

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.0977. Min Act: -0.0000

Data Index: 1449866 (Python Code)

Max Activating Token Index: 118

Text #8

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9665. Min Act: -0.0000

Data Index: 532308 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1584041 (Python Code)

Max Activating Token Index: 995

Text #10

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9216. Min Act: -0.0000

Data Index: 458561 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9854. Min Act: -0.0000

Data Index: 1536849 (Python Code)

Max Activating Token Index: 900

Text #12

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9761. Min Act: -0.0000

Data Index: 1575502 (Python Code)

Max Activating Token Index: 454

Text #13

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8624. Min Act: -0.0000

Data Index: 1312847 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8893. Min Act: -0.0000

Data Index: 1610362 (Python Code)

Max Activating Token Index: 774

Text #15

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8482. Min Act: -0.0000

Data Index: 1530246 (Python Code)

Max Activating Token Index: 827

Text #16

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9049. Min Act: -0.0000

Data Index: 146283 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8502. Min Act: -0.0000

Data Index: 1425400 (Python Code)

Max Activating Token Index: 159

Text #18

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1463987 (Python Code)

Max Activating Token Index: 926

Text #19

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8459. Min Act: -0.0000

Data Index: 1408201 (Python Code)

Max Activating Token Index: 36