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

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

Neuron 2466 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: 3.5445. Min Range: -3.5445

Max Act: 3.5445. Min Act: -0.0000

Data Index: 388085 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 3.5445. Min Range: -3.5445

Max Act: 3.2934. Min Act: -0.0000

Data Index: 203768 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 3.5445. Min Range: -3.5445

Max Act: 3.2811. Min Act: -0.0000

Data Index: 370730 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 3.5445. Min Range: -3.5445

Max Act: 3.2843. Min Act: -0.0000

Data Index: 1044444 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 3.5445. Min Range: -3.5445

Max Act: 3.2253. Min Act: -0.0000

Data Index: 383447 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 3.5445. Min Range: -3.5445

Max Act: 2.8590. Min Act: -0.0000

Data Index: 526093 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 3.5445. Min Range: -3.5445

Max Act: 2.5701. Min Act: -0.0000

Data Index: 840275 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 3.5445. Min Range: -3.5445

Max Act: 2.3014. Min Act: -0.0000

Data Index: 911509 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 3.5445. Min Range: -3.5445

Max Act: 2.1500. Min Act: -0.0000

Data Index: 948273 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 3.5445. Min Range: -3.5445

Max Act: 1.9860. Min Act: -0.0000

Data Index: 950551 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 3.5445. Min Range: -3.5445

Max Act: 2.0967. Min Act: -0.0000

Data Index: 579755 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 3.5445. Min Range: -3.5445

Max Act: 1.9158. Min Act: -0.0000

Data Index: 55423 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 3.5445. Min Range: -3.5445

Max Act: 1.9898. Min Act: -0.0000

Data Index: 1025532 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 3.5445. Min Range: -3.5445

Max Act: 1.8548. Min Act: -0.0000

Data Index: 697614 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 3.5445. Min Range: -3.5445

Max Act: 1.8598. Min Act: -0.0000

Data Index: 206724 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 3.5445. Min Range: -3.5445

Max Act: 1.7243. Min Act: -0.0000

Data Index: 881985 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 3.5445. Min Range: -3.5445

Max Act: 1.7216. Min Act: -0.0000

Data Index: 822563 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 3.5445. Min Range: -3.5445

Max Act: 1.8057. Min Act: -0.0000

Data Index: 126063 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 3.5445. Min Range: -3.5445

Max Act: 1.8013. Min Act: -0.0000

Data Index: 1024981 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 3.5445. Min Range: -3.5445

Max Act: 1.7836. Min Act: -0.0000

Data Index: 132169 (C4 (Web Text))

Max Activating Token Index: 394