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

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

Neuron 1810 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9628. Min Range: -1.9628

Max Act: 1.6203. Min Act: -0.0001

Data Index: 380322 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 1.9628. Min Range: -1.9628

Max Act: 1.9628. Min Act: -0.0001

Data Index: 300526 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 1.9628. Min Range: -1.9628

Max Act: 1.7018. Min Act: -0.0001

Data Index: 291264 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 1.9628. Min Range: -1.9628

Max Act: 1.7920. Min Act: -0.0001

Data Index: 619048 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 1.9628. Min Range: -1.9628

Max Act: 1.6354. Min Act: -0.0001

Data Index: 362874 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 1.9628. Min Range: -1.9628

Max Act: 1.7192. Min Act: -0.0001

Data Index: 597906 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 1.9628. Min Range: -1.9628

Max Act: 1.6782. Min Act: -0.0001

Data Index: 152986 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 1.9628. Min Range: -1.9628

Max Act: 1.6545. Min Act: -0.0001

Data Index: 5711 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 1.9628. Min Range: -1.9628

Max Act: 1.6216. Min Act: -0.0001

Data Index: 518350 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 1.9628. Min Range: -1.9628

Max Act: 1.7105. Min Act: -0.0001

Data Index: 835991 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 1.9628. Min Range: -1.9628

Max Act: 1.6110. Min Act: -0.0001

Data Index: 1582511 (Python Code)

Max Activating Token Index: 2

Text #11

Max Range: 1.9628. Min Range: -1.9628

Max Act: 1.6110. Min Act: -0.0001

Data Index: 906045 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 1.9628. Min Range: -1.9628

Max Act: 1.3406. Min Act: -0.0001

Data Index: 704299 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 1.9628. Min Range: -1.9628

Max Act: 1.4955. Min Act: -0.0001

Data Index: 179267 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 1.9628. Min Range: -1.9628

Max Act: 1.6823. Min Act: -0.0001

Data Index: 87985 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 1.9628. Min Range: -1.9628

Max Act: 1.5730. Min Act: -0.0001

Data Index: 207688 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 1.9628. Min Range: -1.9628

Max Act: 1.5004. Min Act: -0.0001

Data Index: 408122 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 1.9628. Min Range: -1.9628

Max Act: 1.5671. Min Act: -0.0001

Data Index: 560605 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 1.9628. Min Range: -1.9628

Max Act: 1.6419. Min Act: -0.0001

Data Index: 772441 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 1.9628. Min Range: -1.9628

Max Act: 1.4740. Min Act: -0.0001

Data Index: 398640 (C4 (Web Text))

Max Activating Token Index: 64