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

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

Neuron 1857 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: 0.1075. Min Range: -0.1075

Max Act: 0.1075. Min Act: -0.0002

Data Index: 954000 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0948. Min Act: -0.0002

Data Index: 488338 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1087339 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0921. Min Act: -0.0002

Data Index: 187969 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0939. Min Act: -0.0002

Data Index: 161334 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0860. Min Act: -0.0002

Data Index: 451674 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0851. Min Act: -0.0002

Data Index: 1349576 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0858. Min Act: -0.0002

Data Index: 349953 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0860. Min Act: -0.0002

Data Index: 903498 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0826. Min Act: -0.0002

Data Index: 472085 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0858. Min Act: -0.0002

Data Index: 872026 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0813. Min Act: -0.0002

Data Index: 73027 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0816. Min Act: -0.0002

Data Index: 474515 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0835. Min Act: -0.0002

Data Index: 192432 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0803. Min Act: -0.0002

Data Index: 922137 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0739. Min Act: -0.0002

Data Index: 375074 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0725. Min Act: -0.0002

Data Index: 272242 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0807. Min Act: -0.0002

Data Index: 542551 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0839. Min Act: -0.0002

Data Index: 409609 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1302127 (C4 (Web Text))

Max Activating Token Index: 656