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

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

Neuron 5874 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6424. Min Range: -2.6424

Max Act: 2.6424. Min Act: -0.0000

Data Index: 165154 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 2.6424. Min Range: -2.6424

Max Act: 2.1010. Min Act: -0.0000

Data Index: 813878 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 2.6424. Min Range: -2.6424

Max Act: 2.1068. Min Act: -0.0000

Data Index: 1067127 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 2.6424. Min Range: -2.6424

Max Act: 2.0748. Min Act: -0.0000

Data Index: 990960 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 2.6424. Min Range: -2.6424

Max Act: 1.9359. Min Act: -0.0000

Data Index: 8564 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 2.6424. Min Range: -2.6424

Max Act: 1.7543. Min Act: -0.0000

Data Index: 64288 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 2.6424. Min Range: -2.6424

Max Act: 1.7458. Min Act: -0.0000

Data Index: 438417 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 2.6424. Min Range: -2.6424

Max Act: 1.6289. Min Act: -0.0000

Data Index: 695530 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 2.6424. Min Range: -2.6424

Max Act: 1.6237. Min Act: -0.0000

Data Index: 654699 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 2.6424. Min Range: -2.6424

Max Act: 1.8925. Min Act: -0.0000

Data Index: 509248 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 2.6424. Min Range: -2.6424

Max Act: 1.6879. Min Act: -0.0000

Data Index: 304891 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 2.6424. Min Range: -2.6424

Max Act: 1.4907. Min Act: -0.0000

Data Index: 359673 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 2.6424. Min Range: -2.6424

Max Act: 1.7423. Min Act: -0.0000

Data Index: 162411 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 2.6424. Min Range: -2.6424

Max Act: 1.6984. Min Act: -0.0000

Data Index: 117192 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 2.6424. Min Range: -2.6424

Max Act: 1.6266. Min Act: -0.0000

Data Index: 302414 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 2.6424. Min Range: -2.6424

Max Act: 1.6644. Min Act: -0.0000

Data Index: 620677 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 2.6424. Min Range: -2.6424

Max Act: 1.5830. Min Act: -0.0000

Data Index: 404933 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 2.6424. Min Range: -2.6424

Max Act: 1.5814. Min Act: -0.0000

Data Index: 963484 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 2.6424. Min Range: -2.6424

Max Act: 1.5218. Min Act: -0.0000

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 2.6424. Min Range: -2.6424

Max Act: 1.5587. Min Act: -0.0000

Data Index: 169130 (C4 (Web Text))

Max Activating Token Index: 158