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

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

Neuron 5492 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2114. Min Range: -3.2114

Max Act: 3.2114. Min Act: -0.0000

Data Index: 1112876 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 3.2114. Min Range: -3.2114

Max Act: 2.7082. Min Act: -0.0001

Data Index: 272104 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 3.2114. Min Range: -3.2114

Max Act: 2.3116. Min Act: -0.0001

Data Index: 521085 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 3.2114. Min Range: -3.2114

Max Act: 2.1600. Min Act: -0.0001

Data Index: 792288 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 3.2114. Min Range: -3.2114

Max Act: 2.1417. Min Act: -0.0000

Data Index: 413104 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 3.2114. Min Range: -3.2114

Max Act: 2.1369. Min Act: -0.0001

Data Index: 142508 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 3.2114. Min Range: -3.2114

Max Act: 1.9965. Min Act: -0.0001

Data Index: 1325569 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 3.2114. Min Range: -3.2114

Max Act: 2.2185. Min Act: -0.0001

Data Index: 1317853 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 3.2114. Min Range: -3.2114

Max Act: 2.0871. Min Act: -0.0001

Data Index: 929977 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 3.2114. Min Range: -3.2114

Max Act: 2.1808. Min Act: -0.0001

Data Index: 1310865 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 3.2114. Min Range: -3.2114

Max Act: 1.9431. Min Act: -0.0001

Data Index: 1237882 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 3.2114. Min Range: -3.2114

Max Act: 2.0286. Min Act: -0.0001

Data Index: 1195214 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 3.2114. Min Range: -3.2114

Max Act: 2.0396. Min Act: -0.0001

Data Index: 63436 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 3.2114. Min Range: -3.2114

Max Act: 1.8031. Min Act: -0.0001

Data Index: 774299 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 3.2114. Min Range: -3.2114

Max Act: 1.9669. Min Act: -0.0000

Data Index: 1035112 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 3.2114. Min Range: -3.2114

Max Act: 1.9451. Min Act: -0.0001

Data Index: 525233 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 3.2114. Min Range: -3.2114

Max Act: 1.9053. Min Act: -0.0001

Data Index: 1239649 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 3.2114. Min Range: -3.2114

Max Act: 1.8938. Min Act: -0.0000

Data Index: 990259 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 3.2114. Min Range: -3.2114

Max Act: 1.7551. Min Act: -0.0001

Data Index: 203980 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 3.2114. Min Range: -3.2114

Max Act: 1.8711. Min Act: -0.0001

Data Index: 602200 (C4 (Web Text))

Max Activating Token Index: 308