Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2975 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1125. Min Range: -1.1125

Max Act: 1.1125. Min Act: -0.0001

Data Index: 1226639 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9870. Min Act: -0.0001

Data Index: 1215865 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 1.1125. Min Range: -1.1125

Max Act: 1.0194. Min Act: -0.0001

Data Index: 600204 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9682. Min Act: -0.0001

Data Index: 1355326 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9492. Min Act: -0.0001

Data Index: 704171 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9831. Min Act: -0.0001

Data Index: 54472 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9651. Min Act: -0.0001

Data Index: 377504 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9818. Min Act: -0.0001

Data Index: 657829 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9319. Min Act: -0.0001

Data Index: 1098346 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9140. Min Act: -0.0001

Data Index: 931134 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9247. Min Act: -0.0001

Data Index: 310783 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.8923. Min Act: -0.0001

Data Index: 1152676 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9460. Min Act: -0.0001

Data Index: 1262689 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9422. Min Act: -0.0001

Data Index: 255885 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.8291. Min Act: -0.0001

Data Index: 370044 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.8773. Min Act: -0.0001

Data Index: 299877 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9255. Min Act: -0.0001

Data Index: 164124 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9192. Min Act: -0.0001

Data Index: 1328321 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.8838. Min Act: -0.0001

Data Index: 964210 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.8615. Min Act: -0.0001

Data Index: 653085 (C4 (Web Text))

Max Activating Token Index: 727