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

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

Neuron 2794 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: 1.9492. Min Range: -1.9492

Max Act: 1.9492. Min Act: -0.0001

Data Index: 888501 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 1.9492. Min Range: -1.9492

Max Act: 1.6077. Min Act: -0.0001

Data Index: 760743 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 1.9492. Min Range: -1.9492

Max Act: 1.4961. Min Act: -0.0001

Data Index: 1289471 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 1.9492. Min Range: -1.9492

Max Act: 1.5867. Min Act: -0.0001

Data Index: 1033682 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 1.9492. Min Range: -1.9492

Max Act: 1.5514. Min Act: -0.0001

Data Index: 665898 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 1.9492. Min Range: -1.9492

Max Act: 1.5140. Min Act: -0.0001

Data Index: 121286 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 1.9492. Min Range: -1.9492

Max Act: 1.4232. Min Act: -0.0001

Data Index: 1229119 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 1.9492. Min Range: -1.9492

Max Act: 1.4373. Min Act: -0.0001

Data Index: 487218 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 1.9492. Min Range: -1.9492

Max Act: 1.4264. Min Act: -0.0001

Data Index: 996426 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 1.9492. Min Range: -1.9492

Max Act: 1.4180. Min Act: -0.0001

Data Index: 55546 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 1.9492. Min Range: -1.9492

Max Act: 1.4120. Min Act: -0.0001

Data Index: 767609 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 1.9492. Min Range: -1.9492

Max Act: 1.3083. Min Act: -0.0001

Data Index: 381325 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 1.9492. Min Range: -1.9492

Max Act: 1.2898. Min Act: -0.0001

Data Index: 926213 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 1.9492. Min Range: -1.9492

Max Act: 1.2066. Min Act: -0.0001

Data Index: 447728 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 1.9492. Min Range: -1.9492

Max Act: 1.2858. Min Act: -0.0001

Data Index: 679926 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 1.9492. Min Range: -1.9492

Max Act: 1.2028. Min Act: -0.0001

Data Index: 1174952 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 1.9492. Min Range: -1.9492

Max Act: 1.2753. Min Act: -0.0001

Data Index: 496563 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 1.9492. Min Range: -1.9492

Max Act: 1.2993. Min Act: -0.0001

Data Index: 982023 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 1.9492. Min Range: -1.9492

Max Act: 1.2977. Min Act: -0.0001

Data Index: 1239839 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 1.9492. Min Range: -1.9492

Max Act: 1.2589. Min Act: -0.0001

Data Index: 907763 (C4 (Web Text))

Max Activating Token Index: 974