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

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

Neuron 1545 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4142. Min Range: -7.4142

Max Act: 7.4142. Min Act: -0.0000

Data Index: 587623 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 7.4142. Min Range: -7.4142

Max Act: 5.8465. Min Act: -0.0000

Data Index: 966674 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 7.4142. Min Range: -7.4142

Max Act: 5.1252. Min Act: -0.0000

Data Index: 273253 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 7.4142. Min Range: -7.4142

Max Act: 5.4033. Min Act: -0.0000

Data Index: 865703 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 7.4142. Min Range: -7.4142

Max Act: 5.2548. Min Act: -0.0000

Data Index: 275874 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 7.4142. Min Range: -7.4142

Max Act: 5.0814. Min Act: -0.0000

Data Index: 20708 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 7.4142. Min Range: -7.4142

Max Act: 4.7629. Min Act: -0.0000

Data Index: 357429 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 7.4142. Min Range: -7.4142

Max Act: 5.0328. Min Act: -0.0000

Data Index: 1307297 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 7.4142. Min Range: -7.4142

Max Act: 5.0135. Min Act: -0.0000

Data Index: 996129 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 7.4142. Min Range: -7.4142

Max Act: 6.2122. Min Act: -0.0000

Data Index: 988270 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 7.4142. Min Range: -7.4142

Max Act: 4.9103. Min Act: -0.0000

Data Index: 985994 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 7.4142. Min Range: -7.4142

Max Act: 4.5826. Min Act: -0.0000

Data Index: 1310356 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 7.4142. Min Range: -7.4142

Max Act: 5.2074. Min Act: -0.0000

Data Index: 20644 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 7.4142. Min Range: -7.4142

Max Act: 4.5396. Min Act: -0.0000

Data Index: 1329285 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 7.4142. Min Range: -7.4142

Max Act: 4.8741. Min Act: -0.0000

Data Index: 393917 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 7.4142. Min Range: -7.4142

Max Act: 4.7956. Min Act: -0.0000

Data Index: 56670 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 7.4142. Min Range: -7.4142

Max Act: 4.6169. Min Act: -0.0000

Data Index: 1149735 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 7.4142. Min Range: -7.4142

Max Act: 4.7712. Min Act: -0.0000

Data Index: 735404 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 7.4142. Min Range: -7.4142

Max Act: 4.6013. Min Act: -0.0000

Data Index: 1103708 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 7.4142. Min Range: -7.4142

Max Act: 4.3304. Min Act: -0.0000

Data Index: 946952 (C4 (Web Text))

Max Activating Token Index: 262