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

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

Neuron 4243 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9795. Min Range: -3.9795

Max Act: 3.9795. Min Act: -0.0000

Data Index: 617122 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 3.9795. Min Range: -3.9795

Max Act: 3.2057. Min Act: -0.0000

Data Index: 7450 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 3.9795. Min Range: -3.9795

Max Act: 3.3323. Min Act: -0.0000

Data Index: 136477 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 3.9795. Min Range: -3.9795

Max Act: 3.1413. Min Act: -0.0000

Data Index: 406426 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 3.9795. Min Range: -3.9795

Max Act: 2.8822. Min Act: -0.0000

Data Index: 1022154 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 3.9795. Min Range: -3.9795

Max Act: 2.9744. Min Act: -0.0000

Data Index: 29616 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 3.9795. Min Range: -3.9795

Max Act: 2.8916. Min Act: -0.0000

Data Index: 1328884 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 3.9795. Min Range: -3.9795

Max Act: 2.8451. Min Act: -0.0000

Data Index: 1070901 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 3.9795. Min Range: -3.9795

Max Act: 2.7726. Min Act: -0.0000

Data Index: 722574 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 3.9795. Min Range: -3.9795

Max Act: 2.8738. Min Act: -0.0000

Data Index: 1007584 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 3.9795. Min Range: -3.9795

Max Act: 2.6890. Min Act: -0.0000

Data Index: 1013533 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 3.9795. Min Range: -3.9795

Max Act: 2.7936. Min Act: -0.0000

Data Index: 892851 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 3.9795. Min Range: -3.9795

Max Act: 2.6479. Min Act: -0.0000

Data Index: 543920 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 3.9795. Min Range: -3.9795

Max Act: 2.6179. Min Act: -0.0000

Data Index: 645504 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 3.9795. Min Range: -3.9795

Max Act: 2.6198. Min Act: -0.0000

Data Index: 643860 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 3.9795. Min Range: -3.9795

Max Act: 2.4551. Min Act: -0.0000

Data Index: 555956 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 3.9795. Min Range: -3.9795

Max Act: 2.4337. Min Act: -0.0000

Data Index: 31568 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 3.9795. Min Range: -3.9795

Max Act: 2.4039. Min Act: -0.0000

Data Index: 321171 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 3.9795. Min Range: -3.9795

Max Act: 2.3857. Min Act: -0.0000

Data Index: 752414 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 3.9795. Min Range: -3.9795

Max Act: 2.5146. Min Act: -0.0000

Data Index: 1122603 (C4 (Web Text))

Max Activating Token Index: 992