Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1420 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6698. Min Act: -0.0001

Data Index: 810294 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6888. Min Act: -0.0001

Data Index: 110711 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6249. Min Act: -0.0001

Data Index: 1241813 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6179. Min Act: -0.0001

Data Index: 490324 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6282. Min Act: -0.0001

Data Index: 543514 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6045. Min Act: -0.0001

Data Index: 714841 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5672. Min Act: -0.0001

Data Index: 1095743 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5762. Min Act: -0.0001

Data Index: 379914 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5772. Min Act: -0.0001

Data Index: 706631 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5894. Min Act: -0.0001

Data Index: 935368 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5885. Min Act: -0.0001

Data Index: 75356 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5818. Min Act: -0.0001

Data Index: 950828 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5785. Min Act: -0.0001

Data Index: 959634 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5784. Min Act: -0.0001

Data Index: 308696 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5464. Min Act: -0.0001

Data Index: 1123088 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5594. Min Act: -0.0001

Data Index: 867709 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5585. Min Act: -0.0001

Data Index: 252040 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5331. Min Act: -0.0001

Data Index: 368889 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5020. Min Act: -0.0001

Data Index: 308928 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5707. Min Act: -0.0001

Data Index: 491653 (C4 (Web Text))

Max Activating Token Index: 660