Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 18 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4185. Min Range: -3.4185

Max Act: 3.4185. Min Act: -0.0000

Data Index: 663026 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 3.4185. Min Range: -3.4185

Max Act: 3.3801. Min Act: -0.0000

Data Index: 1275392 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 3.4185. Min Range: -3.4185

Max Act: 3.1006. Min Act: -0.0000

Data Index: 1070485 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 3.4185. Min Range: -3.4185

Max Act: 3.2484. Min Act: -0.0000

Data Index: 445379 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 3.4185. Min Range: -3.4185

Max Act: 3.0902. Min Act: -0.0000

Data Index: 767657 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 3.4185. Min Range: -3.4185

Max Act: 3.2107. Min Act: -0.0000

Data Index: 1316611 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 3.4185. Min Range: -3.4185

Max Act: 2.8766. Min Act: -0.0000

Data Index: 721817 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 3.4185. Min Range: -3.4185

Max Act: 3.0164. Min Act: -0.0000

Data Index: 692780 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 3.4185. Min Range: -3.4185

Max Act: 3.0059. Min Act: -0.0000

Data Index: 724108 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 3.4185. Min Range: -3.4185

Max Act: 3.0167. Min Act: -0.0000

Data Index: 19453 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 3.4185. Min Range: -3.4185

Max Act: 2.8751. Min Act: -0.0000

Data Index: 281347 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 3.4185. Min Range: -3.4185

Max Act: 3.0073. Min Act: -0.0000

Data Index: 544743 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 3.4185. Min Range: -3.4185

Max Act: 2.9764. Min Act: -0.0000

Data Index: 1112902 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 3.4185. Min Range: -3.4185

Max Act: 2.8287. Min Act: -0.0000

Data Index: 163738 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 3.4185. Min Range: -3.4185

Max Act: 2.9601. Min Act: -0.0000

Data Index: 80099 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 3.4185. Min Range: -3.4185

Max Act: 2.9287. Min Act: -0.0000

Data Index: 626123 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 3.4185. Min Range: -3.4185

Max Act: 2.9221. Min Act: -0.0000

Data Index: 739706 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 3.4185. Min Range: -3.4185

Max Act: 2.9172. Min Act: -0.0000

Data Index: 1207818 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 3.4185. Min Range: -3.4185

Max Act: 2.8890. Min Act: -0.0000

Data Index: 661163 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 3.4185. Min Range: -3.4185

Max Act: 3.1790. Min Act: -0.0000

Data Index: 1118884 (C4 (Web Text))

Max Activating Token Index: 832