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

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

Neuron 2868 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2669. Min Range: -1.2669

Max Act: 1.2669. Min Act: -0.0000

Data Index: 481040 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 1.2669. Min Range: -1.2669

Max Act: 1.0173. Min Act: -0.0000

Data Index: 47858 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 1.2669. Min Range: -1.2669

Max Act: 1.1216. Min Act: -0.0000

Data Index: 849635 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 1.2669. Min Range: -1.2669

Max Act: 1.0422. Min Act: -0.0000

Data Index: 1189962 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 1.2669. Min Range: -1.2669

Max Act: 1.0443. Min Act: -0.0000

Data Index: 633277 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 1.2669. Min Range: -1.2669

Max Act: 1.0371. Min Act: -0.0000

Data Index: 515459 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 1.2669. Min Range: -1.2669

Max Act: 1.0089. Min Act: -0.0000

Data Index: 1353764 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 1.2669. Min Range: -1.2669

Max Act: 1.0300. Min Act: -0.0000

Data Index: 359421 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 1.2669. Min Range: -1.2669

Max Act: 1.1232. Min Act: -0.0000

Data Index: 869561 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 1.2669. Min Range: -1.2669

Max Act: 1.0211. Min Act: -0.0000

Data Index: 1075963 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 1.2669. Min Range: -1.2669

Max Act: 1.0971. Min Act: -0.0000

Data Index: 62586 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 1.2669. Min Range: -1.2669

Max Act: 1.0031. Min Act: -0.0000

Data Index: 517531 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.9855. Min Act: -0.0000

Data Index: 271165 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.9358. Min Act: -0.0000

Data Index: 1305723 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.9040. Min Act: -0.0000

Data Index: 924217 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.9112. Min Act: -0.0000

Data Index: 160434 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.9014. Min Act: -0.0000

Data Index: 157307 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.8934. Min Act: -0.0000

Data Index: 519359 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.9181. Min Act: -0.0000

Data Index: 974156 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.9377. Min Act: -0.0000

Data Index: 215881 (C4 (Web Text))

Max Activating Token Index: 466