Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1684 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2977. Min Range: -1.2977

Max Act: 1.2977. Min Act: -0.0000

Data Index: 1487256 (Python Code)

Max Activating Token Index: 873

Text #1

Max Range: 1.2977. Min Range: -1.2977

Max Act: 1.1677. Min Act: -0.0000

Data Index: 470565 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 1.2977. Min Range: -1.2977

Max Act: 1.0878. Min Act: -0.0000

Data Index: 35828 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 1.2977. Min Range: -1.2977

Max Act: 1.1238. Min Act: -0.0000

Data Index: 654778 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 1.2977. Min Range: -1.2977

Max Act: 1.0391. Min Act: -0.0000

Data Index: 1354719 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 1.2977. Min Range: -1.2977

Max Act: 1.0310. Min Act: -0.0000

Data Index: 1066141 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 1.2977. Min Range: -1.2977

Max Act: 0.8418. Min Act: -0.0000

Data Index: 1477047 (Python Code)

Max Activating Token Index: 744

Text #7

Max Range: 1.2977. Min Range: -1.2977

Max Act: 0.9005. Min Act: -0.0000

Data Index: 1458546 (Python Code)

Max Activating Token Index: 227

Text #8

Max Range: 1.2977. Min Range: -1.2977

Max Act: 0.9458. Min Act: -0.0000

Data Index: 245386 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 1.2977. Min Range: -1.2977

Max Act: 0.8810. Min Act: -0.0000

Data Index: 1437802 (Python Code)

Max Activating Token Index: 831

Text #10

Max Range: 1.2977. Min Range: -1.2977

Max Act: 0.7343. Min Act: -0.0000

Data Index: 442728 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 1.2977. Min Range: -1.2977

Max Act: 0.7775. Min Act: -0.0000

Data Index: 460389 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 1.2977. Min Range: -1.2977

Max Act: 0.7798. Min Act: -0.0000

Data Index: 1202655 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 1.2977. Min Range: -1.2977

Max Act: 0.7051. Min Act: -0.0000

Data Index: 836636 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 1.2977. Min Range: -1.2977

Max Act: 0.7883. Min Act: -0.0000

Data Index: 660063 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 1.2977. Min Range: -1.2977

Max Act: 0.7884. Min Act: -0.0000

Data Index: 1379176 (Python Code)

Max Activating Token Index: 220

Text #16

Max Range: 1.2977. Min Range: -1.2977

Max Act: 0.7832. Min Act: -0.0000

Data Index: 782377 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 1.2977. Min Range: -1.2977

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1397605 (Python Code)

Max Activating Token Index: 458

Text #18

Max Range: 1.2977. Min Range: -1.2977

Max Act: 0.6653. Min Act: -0.0000

Data Index: 1518056 (Python Code)

Max Activating Token Index: 581

Text #19

Max Range: 1.2977. Min Range: -1.2977

Max Act: 0.6991. Min Act: -0.0000

Data Index: 1521777 (Python Code)

Max Activating Token Index: 181