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

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

Neuron 700 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.5899. Min Act: -0.0002

Data Index: 730696 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.5760. Min Act: -0.0002

Data Index: 174443 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4729. Min Act: -0.0002

Data Index: 1014148 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.5258. Min Act: -0.0002

Data Index: 1240079 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.5298. Min Act: -0.0002

Data Index: 55924 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4996. Min Act: -0.0002

Data Index: 1263200 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4920. Min Act: -0.0002

Data Index: 691072 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4699. Min Act: -0.0002

Data Index: 905064 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4855. Min Act: -0.0002

Data Index: 727164 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4835. Min Act: -0.0002

Data Index: 913965 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4604. Min Act: -0.0002

Data Index: 1057018 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4665. Min Act: -0.0002

Data Index: 822807 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4746. Min Act: -0.0002

Data Index: 1095207 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4400. Min Act: -0.0002

Data Index: 692414 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4667. Min Act: -0.0002

Data Index: 824240 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4424. Min Act: -0.0002

Data Index: 236503 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4642. Min Act: -0.0002

Data Index: 395304 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4884. Min Act: -0.0002

Data Index: 564190 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4339. Min Act: -0.0002

Data Index: 102783 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.5899. Min Range: -0.5899

Max Act: 0.4085. Min Act: -0.0002

Data Index: 209837 (C4 (Web Text))

Max Activating Token Index: 653