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

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

Neuron 1065 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.7424. Min Act: -0.0000

Data Index: 979742 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.5296. Min Act: -0.0000

Data Index: 875341 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.3543. Min Act: -0.0000

Data Index: 656193 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.2431. Min Act: -0.0000

Data Index: 985322 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.1736. Min Act: -0.0000

Data Index: 495981 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.2878. Min Act: -0.0000

Data Index: 353666 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.2448. Min Act: -0.0001

Data Index: 57970 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 4.7424. Min Range: -4.7424

Max Act: 3.8494. Min Act: -0.0000

Data Index: 1141736 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.1568. Min Act: -0.0001

Data Index: 1062980 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 4.7424. Min Range: -4.7424

Max Act: 3.9082. Min Act: -0.0000

Data Index: 55462 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 4.7424. Min Range: -4.7424

Max Act: 3.5557. Min Act: -0.0001

Data Index: 780233 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 4.7424. Min Range: -4.7424

Max Act: 3.7234. Min Act: -0.0001

Data Index: 191030 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.0109. Min Act: -0.0000

Data Index: 166229 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.0335. Min Act: -0.0000

Data Index: 792162 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 4.7424. Min Range: -4.7424

Max Act: 3.8429. Min Act: -0.0000

Data Index: 1321426 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 4.7424. Min Range: -4.7424

Max Act: 3.8491. Min Act: -0.0000

Data Index: 778354 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 4.7424. Min Range: -4.7424

Max Act: 3.7152. Min Act: -0.0000

Data Index: 370118 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 4.7424. Min Range: -4.7424

Max Act: 3.9662. Min Act: -0.0000

Data Index: 613232 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 4.7424. Min Range: -4.7424

Max Act: 3.8199. Min Act: -0.0000

Data Index: 1126626 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 4.7424. Min Range: -4.7424

Max Act: 3.7821. Min Act: -0.0000

Data Index: 1130817 (C4 (Web Text))

Max Activating Token Index: 558