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

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

Neuron 1515 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: 0.9437. Min Range: -0.9437

Max Act: 0.9437. Min Act: -0.0000

Data Index: 293759 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.7913. Min Act: -0.0000

Data Index: 1556229 (Python Code)

Max Activating Token Index: 566

Text #2

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1378934 (Python Code)

Max Activating Token Index: 744

Text #3

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.6054. Min Act: -0.0000

Data Index: 1394048 (Python Code)

Max Activating Token Index: 807

Text #4

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.6793. Min Act: -0.0000

Data Index: 106552 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.6294. Min Act: -0.0000

Data Index: 1063451 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.6354. Min Act: -0.0000

Data Index: 1342864 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.5966. Min Act: -0.0000

Data Index: 34623 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.6020. Min Act: -0.0000

Data Index: 686628 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.6150. Min Act: -0.0000

Data Index: 747771 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.6135. Min Act: -0.0000

Data Index: 781217 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.5495. Min Act: -0.0000

Data Index: 219600 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.5879. Min Act: -0.0000

Data Index: 1181417 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.5963. Min Act: -0.0000

Data Index: 811414 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.5584. Min Act: -0.0000

Data Index: 851378 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.5403. Min Act: -0.0000

Data Index: 30749 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.5798. Min Act: -0.0000

Data Index: 773793 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.5656. Min Act: -0.0000

Data Index: 824162 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.5546. Min Act: -0.0000

Data Index: 504675 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.5097. Min Act: -0.0000

Data Index: 1621538 (Python Code)

Max Activating Token Index: 482