Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1454 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4613. Min Act: -0.0003

Data Index: 964487 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4777. Min Act: -0.0003

Data Index: 1081722 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4161. Min Act: -0.0003

Data Index: 827393 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4250. Min Act: -0.0003

Data Index: 688370 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4232. Min Act: -0.0003

Data Index: 916106 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4181. Min Act: -0.0003

Data Index: 693807 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4778. Min Act: -0.0003

Data Index: 837125 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4307. Min Act: -0.0003

Data Index: 511637 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4125. Min Act: -0.0003

Data Index: 723177 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4092. Min Act: -0.0003

Data Index: 1341442 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4091. Min Act: -0.0003

Data Index: 328005 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4203. Min Act: -0.0003

Data Index: 479548 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4074. Min Act: -0.0003

Data Index: 1003901 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4033. Min Act: -0.0003

Data Index: 437877 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.3911. Min Act: -0.0003

Data Index: 874350 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.3640. Min Act: -0.0003

Data Index: 185462 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4140. Min Act: -0.0003

Data Index: 674643 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4278. Min Act: -0.0003

Data Index: 929069 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.3919. Min Act: -0.0003

Data Index: 196740 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.3834. Min Act: -0.0003

Data Index: 639277 (C4 (Web Text))

Max Activating Token Index: 226