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

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

Neuron 1627 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0918. Min Act: -0.0001

Data Index: 1072241 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1259739 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0938. Min Act: -0.0001

Data Index: 243305 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0910. Min Act: -0.0001

Data Index: 1213792 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0896. Min Act: -0.0001

Data Index: 868359 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0861. Min Act: -0.0001

Data Index: 276920 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0854. Min Act: -0.0001

Data Index: 1018142 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1224764 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0884. Min Act: -0.0001

Data Index: 1105617 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0829. Min Act: -0.0001

Data Index: 371465 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1305035 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0822. Min Act: -0.0001

Data Index: 962215 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0815. Min Act: -0.0001

Data Index: 240539 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0804. Min Act: -0.0001

Data Index: 524151 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0812. Min Act: -0.0001

Data Index: 879508 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0813. Min Act: -0.0001

Data Index: 1350171 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0744. Min Act: -0.0001

Data Index: 560590 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0768. Min Act: -0.0001

Data Index: 387676 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0791. Min Act: -0.0001

Data Index: 924342 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0796. Min Act: -0.0001

Data Index: 1141862 (C4 (Web Text))

Max Activating Token Index: 557