Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 154 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2068. Min Range: -1.2068

Max Act: 1.2068. Min Act: -0.0002

Data Index: 401730 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 1.2068. Min Range: -1.2068

Max Act: 1.0109. Min Act: -0.0002

Data Index: 766250 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 1.2068. Min Range: -1.2068

Max Act: 0.8472. Min Act: -0.0002

Data Index: 381328 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 1.2068. Min Range: -1.2068

Max Act: 0.8811. Min Act: -0.0001

Data Index: 23717 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 1.2068. Min Range: -1.2068

Max Act: 0.7831. Min Act: -0.0001

Data Index: 1348900 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 1.2068. Min Range: -1.2068

Max Act: 0.8133. Min Act: -0.0001

Data Index: 869153 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 1.2068. Min Range: -1.2068

Max Act: 0.7897. Min Act: -0.0002

Data Index: 1069966 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 1.2068. Min Range: -1.2068

Max Act: 0.7813. Min Act: -0.0002

Data Index: 1085770 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 1.2068. Min Range: -1.2068

Max Act: 0.7642. Min Act: -0.0001

Data Index: 237902 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 1.2068. Min Range: -1.2068

Max Act: 0.7484. Min Act: -0.0002

Data Index: 499582 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 1.2068. Min Range: -1.2068

Max Act: 0.8194. Min Act: -0.0002

Data Index: 1289535 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 1.2068. Min Range: -1.2068

Max Act: 0.7548. Min Act: -0.0001

Data Index: 292183 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 1.2068. Min Range: -1.2068

Max Act: 0.6819. Min Act: -0.0002

Data Index: 758526 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 1.2068. Min Range: -1.2068

Max Act: 0.7288. Min Act: -0.0001

Data Index: 123322 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 1.2068. Min Range: -1.2068

Max Act: 0.7185. Min Act: -0.0002

Data Index: 1072473 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 1.2068. Min Range: -1.2068

Max Act: 0.7849. Min Act: -0.0001

Data Index: 485120 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 1.2068. Min Range: -1.2068

Max Act: 0.7057. Min Act: -0.0002

Data Index: 689468 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 1.2068. Min Range: -1.2068

Max Act: 0.7641. Min Act: -0.0002

Data Index: 887032 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 1.2068. Min Range: -1.2068

Max Act: 0.7194. Min Act: -0.0002

Data Index: 26116 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 1.2068. Min Range: -1.2068

Max Act: 0.6978. Min Act: -0.0001

Data Index: 923808 (C4 (Web Text))

Max Activating Token Index: 464