Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3147 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1887. Min Range: -1.1887

Max Act: 1.1887. Min Act: -0.0000

Data Index: 612487 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 1.1887. Min Range: -1.1887

Max Act: 1.1422. Min Act: -0.0000

Data Index: 995958 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 1.1887. Min Range: -1.1887

Max Act: 1.1225. Min Act: -0.0000

Data Index: 1309267 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 1.1887. Min Range: -1.1887

Max Act: 1.1300. Min Act: -0.0000

Data Index: 956141 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.9402. Min Act: -0.0000

Data Index: 852134 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 1.1887. Min Range: -1.1887

Max Act: 1.0439. Min Act: -0.0000

Data Index: 859339 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.9462. Min Act: -0.0000

Data Index: 332689 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.9781. Min Act: -0.0000

Data Index: 568966 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.8951. Min Act: -0.0000

Data Index: 303235 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.8634. Min Act: -0.0000

Data Index: 269224 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.9157. Min Act: -0.0000

Data Index: 2725 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.8954. Min Act: -0.0000

Data Index: 743930 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.7724. Min Act: -0.0000

Data Index: 141080 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1052797 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.7595. Min Act: -0.0000

Data Index: 193010 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.7488. Min Act: -0.0000

Data Index: 1098567 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.7676. Min Act: -0.0000

Data Index: 897351 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.7417. Min Act: -0.0000

Data Index: 102594 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.7591. Min Act: -0.0000

Data Index: 151447 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.7318. Min Act: -0.0000

Data Index: 321189 (C4 (Web Text))

Max Activating Token Index: 636