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

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

Neuron 1277 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.2155. Min Act: -0.0000

Data Index: 970029 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.0249. Min Act: -0.0000

Data Index: 259193 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 3.2155. Min Range: -3.2155

Max Act: 2.9797. Min Act: -0.0000

Data Index: 685536 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 3.2155. Min Range: -3.2155

Max Act: 2.7971. Min Act: -0.0000

Data Index: 752568 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 3.2155. Min Range: -3.2155

Max Act: 2.4400. Min Act: -0.0000

Data Index: 303542 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 3.2155. Min Range: -3.2155

Max Act: 2.4594. Min Act: -0.0000

Data Index: 664964 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 3.2155. Min Range: -3.2155

Max Act: 2.7137. Min Act: -0.0000

Data Index: 302120 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 3.2155. Min Range: -3.2155

Max Act: 2.3609. Min Act: -0.0000

Data Index: 798157 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 3.2155. Min Range: -3.2155

Max Act: 2.3658. Min Act: -0.0000

Data Index: 310198 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 3.2155. Min Range: -3.2155

Max Act: 2.4773. Min Act: -0.0000

Data Index: 634753 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 3.2155. Min Range: -3.2155

Max Act: 2.6021. Min Act: -0.0000

Data Index: 1001269 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 3.2155. Min Range: -3.2155

Max Act: 2.3285. Min Act: -0.0000

Data Index: 1205755 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 3.2155. Min Range: -3.2155

Max Act: 2.3852. Min Act: -0.0000

Data Index: 1191919 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 3.2155. Min Range: -3.2155

Max Act: 2.3707. Min Act: -0.0000

Data Index: 584045 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 3.2155. Min Range: -3.2155

Max Act: 2.3716. Min Act: -0.0000

Data Index: 605330 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 3.2155. Min Range: -3.2155

Max Act: 2.3731. Min Act: -0.0000

Data Index: 852402 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 3.2155. Min Range: -3.2155

Max Act: 2.4406. Min Act: -0.0000

Data Index: 980023 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 3.2155. Min Range: -3.2155

Max Act: 2.3159. Min Act: -0.0000

Data Index: 1060294 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 3.2155. Min Range: -3.2155

Max Act: 2.2932. Min Act: -0.0000

Data Index: 1067159 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 3.2155. Min Range: -3.2155

Max Act: 2.4161. Min Act: -0.0000

Data Index: 1323733 (C4 (Web Text))

Max Activating Token Index: 352