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

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

Neuron 5579 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1341. Min Range: -3.1341

Max Act: 3.1341. Min Act: -0.0000

Data Index: 985988 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 3.1341. Min Range: -3.1341

Max Act: 2.9833. Min Act: -0.0000

Data Index: 64167 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 3.1341. Min Range: -3.1341

Max Act: 2.9408. Min Act: -0.0000

Data Index: 1212383 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 3.1341. Min Range: -3.1341

Max Act: 3.0295. Min Act: -0.0000

Data Index: 1001313 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 3.1341. Min Range: -3.1341

Max Act: 2.8732. Min Act: -0.0000

Data Index: 283127 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 3.1341. Min Range: -3.1341

Max Act: 2.8405. Min Act: -0.0000

Data Index: 365416 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 3.1341. Min Range: -3.1341

Max Act: 2.7591. Min Act: -0.0000

Data Index: 1304083 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 3.1341. Min Range: -3.1341

Max Act: 2.6410. Min Act: -0.0000

Data Index: 92241 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 3.1341. Min Range: -3.1341

Max Act: 2.6186. Min Act: -0.0000

Data Index: 458906 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 3.1341. Min Range: -3.1341

Max Act: 2.5992. Min Act: -0.0000

Data Index: 722471 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 3.1341. Min Range: -3.1341

Max Act: 2.5750. Min Act: -0.0000

Data Index: 59883 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 3.1341. Min Range: -3.1341

Max Act: 2.7007. Min Act: -0.0000

Data Index: 578804 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 3.1341. Min Range: -3.1341

Max Act: 2.5350. Min Act: -0.0000

Data Index: 1301672 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 3.1341. Min Range: -3.1341

Max Act: 2.3649. Min Act: -0.0000

Data Index: 553172 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 3.1341. Min Range: -3.1341

Max Act: 2.4955. Min Act: -0.0000

Data Index: 60501 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 3.1341. Min Range: -3.1341

Max Act: 2.4500. Min Act: -0.0000

Data Index: 1028306 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 3.1341. Min Range: -3.1341

Max Act: 2.4146. Min Act: -0.0000

Data Index: 1077170 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 3.1341. Min Range: -3.1341

Max Act: 2.2852. Min Act: -0.0000

Data Index: 334645 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 3.1341. Min Range: -3.1341

Max Act: 2.5142. Min Act: -0.0000

Data Index: 1354690 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 3.1341. Min Range: -3.1341

Max Act: 2.4793. Min Act: -0.0000

Data Index: 1171314 (C4 (Web Text))

Max Activating Token Index: 832