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

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

Neuron 822 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.0261. Min Act: -0.0001

Data Index: 1236652 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.6591. Min Act: -0.0001

Data Index: 1530882 (Python Code)

Max Activating Token Index: 235

Text #2

Max Range: 1.6591. Min Range: -1.6591

Max Act: 0.9470. Min Act: -0.0001

Data Index: 1144248 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 1.6591. Min Range: -1.6591

Max Act: 1.0442. Min Act: -0.0001

Data Index: 536929 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 1.6591. Min Range: -1.6591

Max Act: 0.9977. Min Act: -0.0001

Data Index: 699661 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 1.6591. Min Range: -1.6591

Max Act: 0.8638. Min Act: -0.0001

Data Index: 886920 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 1.6591. Min Range: -1.6591

Max Act: 0.8460. Min Act: -0.0001

Data Index: 516293 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 1.6591. Min Range: -1.6591

Max Act: 0.7877. Min Act: -0.0001

Data Index: 1289629 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 1.6591. Min Range: -1.6591

Max Act: 0.8527. Min Act: -0.0001

Data Index: 284430 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 1.6591. Min Range: -1.6591

Max Act: 0.8808. Min Act: -0.0001

Data Index: 1026225 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 1.6591. Min Range: -1.6591

Max Act: 0.9310. Min Act: -0.0001

Data Index: 1033923 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 1.6591. Min Range: -1.6591

Max Act: 0.8193. Min Act: -0.0001

Data Index: 909098 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 1.6591. Min Range: -1.6591

Max Act: 0.8002. Min Act: -0.0001

Data Index: 44479 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 1.6591. Min Range: -1.6591

Max Act: 0.8264. Min Act: -0.0001

Data Index: 1282386 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 1.6591. Min Range: -1.6591

Max Act: 0.8183. Min Act: -0.0001

Data Index: 1300331 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 1.6591. Min Range: -1.6591

Max Act: 0.8906. Min Act: -0.0001

Data Index: 860827 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 1.6591. Min Range: -1.6591

Max Act: 0.7048. Min Act: -0.0001

Data Index: 1313527 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 1.6591. Min Range: -1.6591

Max Act: 0.8121. Min Act: -0.0001

Data Index: 599911 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 1.6591. Min Range: -1.6591

Max Act: 0.7829. Min Act: -0.0001

Data Index: 1325751 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 1.6591. Min Range: -1.6591

Max Act: 0.8005. Min Act: -0.0001

Data Index: 650025 (C4 (Web Text))

Max Activating Token Index: 30