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

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

Neuron 3080 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.7593. Min Act: -0.0000

Data Index: 877318 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1051105 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.6514. Min Act: -0.0000

Data Index: 1294229 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.6152. Min Act: -0.0000

Data Index: 675345 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.6033. Min Act: -0.0000

Data Index: 526797 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.5274. Min Act: -0.0000

Data Index: 440524 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.5194. Min Act: -0.0000

Data Index: 538309 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.4483. Min Act: -0.0000

Data Index: 986751 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.4525. Min Act: -0.0000

Data Index: 1308277 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.4480. Min Act: -0.0000

Data Index: 487651 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.4104. Min Act: -0.0000

Data Index: 366686 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.3552. Min Act: -0.0000

Data Index: 183983 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.3613. Min Act: -0.0000

Data Index: 912298 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.3875. Min Act: -0.0000

Data Index: 117349 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.3333. Min Act: -0.0000

Data Index: 276813 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1343375 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.3565. Min Act: -0.0000

Data Index: 280946 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.3534. Min Act: -0.0000

Data Index: 412167 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.2901. Min Act: -0.0000

Data Index: 443055 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.2949. Min Act: -0.0000

Data Index: 847393 (C4 (Web Text))

Max Activating Token Index: 282