Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 244 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8698. Min Range: -3.8698

Max Act: 3.8698. Min Act: -0.0000

Data Index: 779160 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 3.8698. Min Range: -3.8698

Max Act: 3.1939. Min Act: -0.0000

Data Index: 1379965 (Python Code)

Max Activating Token Index: 53

Text #2

Max Range: 3.8698. Min Range: -3.8698

Max Act: 3.1358. Min Act: -0.0000

Data Index: 550149 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 3.8698. Min Range: -3.8698

Max Act: 2.8274. Min Act: -0.0000

Data Index: 1563749 (Python Code)

Max Activating Token Index: 851

Text #4

Max Range: 3.8698. Min Range: -3.8698

Max Act: 3.0840. Min Act: -0.0000

Data Index: 1492791 (Python Code)

Max Activating Token Index: 424

Text #5

Max Range: 3.8698. Min Range: -3.8698

Max Act: 2.6690. Min Act: -0.0000

Data Index: 1390606 (Python Code)

Max Activating Token Index: 341

Text #6

Max Range: 3.8698. Min Range: -3.8698

Max Act: 2.8354. Min Act: -0.0000

Data Index: 1456135 (Python Code)

Max Activating Token Index: 443

Text #7

Max Range: 3.8698. Min Range: -3.8698

Max Act: 2.9410. Min Act: -0.0000

Data Index: 1559826 (Python Code)

Max Activating Token Index: 495

Text #8

Max Range: 3.8698. Min Range: -3.8698

Max Act: 2.1046. Min Act: -0.0000

Data Index: 845447 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 3.8698. Min Range: -3.8698

Max Act: 2.2618. Min Act: -0.0000

Data Index: 761502 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 3.8698. Min Range: -3.8698

Max Act: 2.0905. Min Act: -0.0000

Data Index: 1329145 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 3.8698. Min Range: -3.8698

Max Act: 2.0161. Min Act: -0.0000

Data Index: 741853 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 3.8698. Min Range: -3.8698

Max Act: 2.1385. Min Act: -0.0000

Data Index: 60983 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 3.8698. Min Range: -3.8698

Max Act: 1.9866. Min Act: -0.0000

Data Index: 334004 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 3.8698. Min Range: -3.8698

Max Act: 1.9642. Min Act: 0.0000

Data Index: 937771 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 3.8698. Min Range: -3.8698

Max Act: 1.8853. Min Act: -0.0000

Data Index: 947308 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 3.8698. Min Range: -3.8698

Max Act: 1.6299. Min Act: -0.0000

Data Index: 1529137 (Python Code)

Max Activating Token Index: 101

Text #17

Max Range: 3.8698. Min Range: -3.8698

Max Act: 1.8457. Min Act: -0.0000

Data Index: 341193 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 3.8698. Min Range: -3.8698

Max Act: 1.9326. Min Act: -0.0000

Data Index: 1112399 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 3.8698. Min Range: -3.8698

Max Act: 1.7658. Min Act: -0.0000

Data Index: 267801 (C4 (Web Text))

Max Activating Token Index: 544