Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4249 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.5129. Min Act: -0.0000

Data Index: 1223249 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1000755 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4855. Min Act: -0.0000

Data Index: 487584 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4560. Min Act: -0.0000

Data Index: 1118531 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1244888 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4046. Min Act: -0.0000

Data Index: 1143517 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4303. Min Act: -0.0000

Data Index: 981065 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4182. Min Act: -0.0000

Data Index: 1284365 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4169. Min Act: -0.0000

Data Index: 825167 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1123570 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3992. Min Act: -0.0000

Data Index: 325817 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3853. Min Act: -0.0000

Data Index: 327847 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3871. Min Act: -0.0000

Data Index: 613940 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3815. Min Act: -0.0000

Data Index: 665065 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3902. Min Act: -0.0000

Data Index: 935706 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3577. Min Act: -0.0000

Data Index: 666982 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3839. Min Act: -0.0000

Data Index: 729522 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3586. Min Act: -0.0000

Data Index: 34037 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3796. Min Act: -0.0000

Data Index: 45451 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1266057 (C4 (Web Text))

Max Activating Token Index: 257