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

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

Neuron 4568 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: 3.1269. Min Range: -3.1269

Max Act: 3.1269. Min Act: -0.0000

Data Index: 324675 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 3.1269. Min Range: -3.1269

Max Act: 2.7448. Min Act: -0.0000

Data Index: 357952 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 3.1269. Min Range: -3.1269

Max Act: 2.8206. Min Act: -0.0000

Data Index: 1089983 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 3.1269. Min Range: -3.1269

Max Act: 2.4856. Min Act: -0.0000

Data Index: 89843 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 3.1269. Min Range: -3.1269

Max Act: 2.4990. Min Act: -0.0000

Data Index: 1278159 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 3.1269. Min Range: -3.1269

Max Act: 2.2167. Min Act: -0.0000

Data Index: 207233 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 3.1269. Min Range: -3.1269

Max Act: 2.0158. Min Act: -0.0000

Data Index: 1017808 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 3.1269. Min Range: -3.1269

Max Act: 1.9666. Min Act: -0.0000

Data Index: 923043 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 3.1269. Min Range: -3.1269

Max Act: 1.8161. Min Act: -0.0000

Data Index: 821693 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 3.1269. Min Range: -3.1269

Max Act: 1.8988. Min Act: -0.0000

Data Index: 1077008 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 3.1269. Min Range: -3.1269

Max Act: 1.8334. Min Act: -0.0000

Data Index: 573117 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 3.1269. Min Range: -3.1269

Max Act: 1.8507. Min Act: -0.0000

Data Index: 901363 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 3.1269. Min Range: -3.1269

Max Act: 1.7012. Min Act: -0.0000

Data Index: 897668 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 3.1269. Min Range: -3.1269

Max Act: 1.9449. Min Act: -0.0000

Data Index: 131673 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 3.1269. Min Range: -3.1269

Max Act: 1.7036. Min Act: -0.0000

Data Index: 946320 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 3.1269. Min Range: -3.1269

Max Act: 1.6974. Min Act: -0.0000

Data Index: 757049 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 3.1269. Min Range: -3.1269

Max Act: 1.8441. Min Act: -0.0000

Data Index: 496117 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 3.1269. Min Range: -3.1269

Max Act: 1.7543. Min Act: -0.0000

Data Index: 707779 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 3.1269. Min Range: -3.1269

Max Act: 1.8198. Min Act: -0.0000

Data Index: 482953 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 3.1269. Min Range: -3.1269

Max Act: 1.8527. Min Act: -0.0000

Data Index: 155790 (C4 (Web Text))

Max Activating Token Index: 300