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

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

Neuron 4440 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.9133. Min Act: -0.0001

Data Index: 218261 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.5077. Min Act: -0.0001

Data Index: 1352665 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.4158. Min Act: -0.0001

Data Index: 116922 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.2653. Min Act: -0.0001

Data Index: 946074 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.4954. Min Act: -0.0001

Data Index: 1305718 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.4391. Min Act: -0.0001

Data Index: 622753 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.4737. Min Act: -0.0001

Data Index: 1006639 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.3159. Min Act: -0.0001

Data Index: 161845 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.3417. Min Act: -0.0001

Data Index: 707817 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.3795. Min Act: -0.0001

Data Index: 304610 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.1895. Min Act: -0.0001

Data Index: 117063 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.2595. Min Act: -0.0001

Data Index: 932422 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.2996. Min Act: -0.0001

Data Index: 1027105 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.2181. Min Act: -0.0001

Data Index: 347665 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.2291. Min Act: -0.0001

Data Index: 528883 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.2179. Min Act: -0.0001

Data Index: 16659 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.1467. Min Act: -0.0001

Data Index: 548773 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.1770. Min Act: -0.0001

Data Index: 1337590 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.1799. Min Act: -0.0001

Data Index: 1319300 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.2262. Min Act: -0.0001

Data Index: 727286 (C4 (Web Text))

Max Activating Token Index: 994