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

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

Neuron 4354 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: 0.4585. Min Range: -0.4585

Max Act: 0.4499. Min Act: -0.0000

Data Index: 935685 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.4585. Min Act: -0.0000

Data Index: 1254516 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.4389. Min Act: -0.0000

Data Index: 46521 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.4500. Min Act: -0.0000

Data Index: 765652 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.4398. Min Act: -0.0000

Data Index: 238543 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.4105. Min Act: -0.0000

Data Index: 45637 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.4211. Min Act: -0.0000

Data Index: 397466 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3963. Min Act: -0.0000

Data Index: 213019 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.4229. Min Act: -0.0000

Data Index: 338466 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.4280. Min Act: -0.0000

Data Index: 766491 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.4173. Min Act: -0.0000

Data Index: 237124 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3916. Min Act: -0.0000

Data Index: 861318 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3908. Min Act: -0.0000

Data Index: 559383 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.4149. Min Act: -0.0000

Data Index: 892450 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.4098. Min Act: -0.0000

Data Index: 423142 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3928. Min Act: -0.0000

Data Index: 228225 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.4046. Min Act: -0.0000

Data Index: 236242 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3889. Min Act: -0.0000

Data Index: 110506 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3973. Min Act: -0.0000

Data Index: 67429 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3898. Min Act: -0.0000

Data Index: 398268 (C4 (Web Text))

Max Activating Token Index: 857