Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 111 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.6139. Min Act: -0.0006

Data Index: 878067 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.5300. Min Act: -0.0006

Data Index: 1101203 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.5097. Min Act: -0.0006

Data Index: 770359 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.5098. Min Act: -0.0006

Data Index: 1248169 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.5146. Min Act: -0.0006

Data Index: 240547 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.5229. Min Act: -0.0006

Data Index: 1226774 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4541. Min Act: -0.0006

Data Index: 645049 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.5199. Min Act: -0.0006

Data Index: 234663 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4801. Min Act: -0.0006

Data Index: 1169848 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4871. Min Act: -0.0006

Data Index: 204529 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4716. Min Act: -0.0006

Data Index: 822460 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4516. Min Act: -0.0006

Data Index: 623333 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4681. Min Act: -0.0006

Data Index: 903243 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4831. Min Act: -0.0006

Data Index: 445224 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4447. Min Act: -0.0006

Data Index: 413284 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4006. Min Act: -0.0006

Data Index: 678252 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4246. Min Act: -0.0006

Data Index: 845451 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4685. Min Act: -0.0006

Data Index: 1177546 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4035. Min Act: -0.0006

Data Index: 865636 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4643. Min Act: -0.0006

Data Index: 878083 (C4 (Web Text))

Max Activating Token Index: 763