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

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

Neuron 4193 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.6832. Min Act: -0.0001

Data Index: 263138 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.6592. Min Act: -0.0001

Data Index: 453744 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.6320. Min Act: -0.0001

Data Index: 91122 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5976. Min Act: -0.0001

Data Index: 713706 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.6534. Min Act: -0.0001

Data Index: 786911 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5600. Min Act: -0.0001

Data Index: 981518 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.6800. Min Act: -0.0001

Data Index: 855473 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5753. Min Act: -0.0001

Data Index: 834713 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5733. Min Act: -0.0001

Data Index: 179559 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.6247. Min Act: -0.0001

Data Index: 614430 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5815. Min Act: -0.0001

Data Index: 1134398 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5657. Min Act: -0.0001

Data Index: 569489 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.6230. Min Act: -0.0001

Data Index: 325278 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5185. Min Act: -0.0001

Data Index: 830837 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.4805. Min Act: -0.0001

Data Index: 1332985 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5906. Min Act: -0.0001

Data Index: 371278 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5977. Min Act: -0.0001

Data Index: 83457 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5738. Min Act: -0.0001

Data Index: 611917 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5565. Min Act: -0.0001

Data Index: 294452 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.6246. Min Act: -0.0001

Data Index: 131855 (C4 (Web Text))

Max Activating Token Index: 101