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

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

Neuron 280 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.8872. Min Act: -0.0000

Data Index: 867485 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.8189. Min Act: -0.0000

Data Index: 564119 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.7958. Min Act: -0.0000

Data Index: 1342610 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1291681 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.7790. Min Act: -0.0000

Data Index: 980995 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.7192. Min Act: -0.0000

Data Index: 411731 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.7123. Min Act: -0.0000

Data Index: 386071 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.6748. Min Act: -0.0000

Data Index: 435917 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.6443. Min Act: -0.0000

Data Index: 272025 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.6643. Min Act: -0.0000

Data Index: 378781 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.6120. Min Act: -0.0000

Data Index: 1348700 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.5521. Min Act: -0.0000

Data Index: 809860 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.5675. Min Act: -0.0000

Data Index: 734167 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1007936 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.5662. Min Act: -0.0000

Data Index: 990463 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.5058. Min Act: -0.0000

Data Index: 752558 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.4391. Min Act: -0.0000

Data Index: 841478 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.5031. Min Act: -0.0000

Data Index: 300824 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1308735 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 0.8872. Min Range: -0.8872

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1242261 (C4 (Web Text))

Max Activating Token Index: 298