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

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

Neuron 2755 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.8959. Min Act: -0.0000

Data Index: 35461 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.8593. Min Act: -0.0000

Data Index: 872883 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.8124. Min Act: -0.0000

Data Index: 1539009 (Python Code)

Max Activating Token Index: 34

Text #3

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.8029. Min Act: -0.0000

Data Index: 969908 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.7734. Min Act: -0.0000

Data Index: 1549724 (Python Code)

Max Activating Token Index: 458

Text #5

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.7391. Min Act: -0.0000

Data Index: 1452363 (Python Code)

Max Activating Token Index: 71

Text #6

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.7631. Min Act: -0.0000

Data Index: 147784 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.7794. Min Act: -0.0000

Data Index: 1656319 (Python Code)

Max Activating Token Index: 112

Text #8

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.7538. Min Act: -0.0000

Data Index: 1382463 (Python Code)

Max Activating Token Index: 243

Text #9

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.7343. Min Act: -0.0000

Data Index: 1463376 (Python Code)

Max Activating Token Index: 89

Text #10

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.7756. Min Act: -0.0000

Data Index: 1200409 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6977. Min Act: -0.0000

Data Index: 863510 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6818. Min Act: -0.0000

Data Index: 43575 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6191. Min Act: -0.0000

Data Index: 317221 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6697. Min Act: -0.0000

Data Index: 174884 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6752. Min Act: -0.0000

Data Index: 18377 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6669. Min Act: -0.0000

Data Index: 73186 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6474. Min Act: -0.0000

Data Index: 1237151 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6746. Min Act: -0.0000

Data Index: 367781 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6555. Min Act: -0.0000

Data Index: 1542668 (Python Code)

Max Activating Token Index: 145