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

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

Neuron 3186 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: 1.8027. Min Range: -1.8027

Max Act: 1.8027. Min Act: -0.0000

Data Index: 1205111 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 1.8027. Min Range: -1.8027

Max Act: 1.6605. Min Act: -0.0000

Data Index: 1005729 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 1.8027. Min Range: -1.8027

Max Act: 1.6797. Min Act: -0.0000

Data Index: 803746 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 1.8027. Min Range: -1.8027

Max Act: 1.6518. Min Act: -0.0000

Data Index: 20333 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 1.8027. Min Range: -1.8027

Max Act: 1.5379. Min Act: -0.0000

Data Index: 1109829 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 1.8027. Min Range: -1.8027

Max Act: 1.4719. Min Act: -0.0000

Data Index: 296156 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 1.8027. Min Range: -1.8027

Max Act: 1.4105. Min Act: -0.0000

Data Index: 1149640 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 1.8027. Min Range: -1.8027

Max Act: 1.2721. Min Act: -0.0000

Data Index: 831395 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 1.8027. Min Range: -1.8027

Max Act: 1.3394. Min Act: -0.0000

Data Index: 612173 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 1.8027. Min Range: -1.8027

Max Act: 1.3201. Min Act: -0.0000

Data Index: 1185717 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 1.8027. Min Range: -1.8027

Max Act: 1.3249. Min Act: -0.0000

Data Index: 486391 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 1.8027. Min Range: -1.8027

Max Act: 1.3410. Min Act: -0.0000

Data Index: 1351217 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 1.8027. Min Range: -1.8027

Max Act: 1.2635. Min Act: -0.0000

Data Index: 554529 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 1.8027. Min Range: -1.8027

Max Act: 1.3229. Min Act: -0.0000

Data Index: 851234 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 1.8027. Min Range: -1.8027

Max Act: 1.1041. Min Act: -0.0000

Data Index: 969967 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 1.8027. Min Range: -1.8027

Max Act: 1.1024. Min Act: -0.0000

Data Index: 208422 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 1.8027. Min Range: -1.8027

Max Act: 1.1020. Min Act: -0.0000

Data Index: 1349381 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 1.8027. Min Range: -1.8027

Max Act: 1.1410. Min Act: -0.0000

Data Index: 826389 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 1.8027. Min Range: -1.8027

Max Act: 1.2806. Min Act: -0.0000

Data Index: 691568 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 1.8027. Min Range: -1.8027

Max Act: 1.1991. Min Act: -0.0000

Data Index: 1115704 (C4 (Web Text))

Max Activating Token Index: 834