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

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

Neuron 4090 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6716. Min Range: -3.6716

Max Act: 3.6716. Min Act: -0.0000

Data Index: 347430 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 3.6716. Min Range: -3.6716

Max Act: 3.0689. Min Act: -0.0000

Data Index: 962784 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 3.6716. Min Range: -3.6716

Max Act: 2.8344. Min Act: -0.0000

Data Index: 779254 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 3.6716. Min Range: -3.6716

Max Act: 2.4730. Min Act: -0.0000

Data Index: 319166 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 3.6716. Min Range: -3.6716

Max Act: 2.4933. Min Act: -0.0000

Data Index: 450552 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 3.6716. Min Range: -3.6716

Max Act: 2.4983. Min Act: -0.0000

Data Index: 333655 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 3.6716. Min Range: -3.6716

Max Act: 2.3087. Min Act: -0.0000

Data Index: 186099 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 3.6716. Min Range: -3.6716

Max Act: 2.1642. Min Act: -0.0000

Data Index: 728359 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 3.6716. Min Range: -3.6716

Max Act: 2.1261. Min Act: -0.0000

Data Index: 18633 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 3.6716. Min Range: -3.6716

Max Act: 1.9768. Min Act: -0.0000

Data Index: 342606 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 3.6716. Min Range: -3.6716

Max Act: 2.2075. Min Act: -0.0000

Data Index: 1280575 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 3.6716. Min Range: -3.6716

Max Act: 1.9339. Min Act: -0.0000

Data Index: 690357 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 3.6716. Min Range: -3.6716

Max Act: 1.9843. Min Act: -0.0000

Data Index: 670552 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 3.6716. Min Range: -3.6716

Max Act: 1.9634. Min Act: -0.0000

Data Index: 27597 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 3.6716. Min Range: -3.6716

Max Act: 1.9460. Min Act: -0.0000

Data Index: 698464 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 3.6716. Min Range: -3.6716

Max Act: 1.8465. Min Act: -0.0000

Data Index: 369262 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 3.6716. Min Range: -3.6716

Max Act: 2.1574. Min Act: -0.0000

Data Index: 529564 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 3.6716. Min Range: -3.6716

Max Act: 1.9217. Min Act: -0.0000

Data Index: 325035 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 3.6716. Min Range: -3.6716

Max Act: 1.9930. Min Act: -0.0000

Data Index: 677004 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 3.6716. Min Range: -3.6716

Max Act: 1.7782. Min Act: -0.0000

Data Index: 481058 (C4 (Web Text))

Max Activating Token Index: 988