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

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

Neuron 577 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.4389. Min Act: -0.0001

Data Index: 820853 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.1492. Min Act: -0.0001

Data Index: 684629 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.1500. Min Act: -0.0001

Data Index: 317090 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.1468. Min Act: -0.0001

Data Index: 247564 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.1553. Min Act: -0.0001

Data Index: 935616 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.0107. Min Act: -0.0001

Data Index: 784828 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.0257. Min Act: -0.0001

Data Index: 235598 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.0482. Min Act: -0.0001

Data Index: 1339927 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.1086. Min Act: -0.0001

Data Index: 249186 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.9960. Min Act: -0.0001

Data Index: 1174157 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.0671. Min Act: -0.0001

Data Index: 950118 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.9976. Min Act: -0.0001

Data Index: 1179260 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.9596. Min Act: -0.0001

Data Index: 718184 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.9692. Min Act: -0.0001

Data Index: 447317 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.9317. Min Act: -0.0001

Data Index: 799488 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.9894. Min Act: -0.0001

Data Index: 571877 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.9400. Min Act: -0.0001

Data Index: 103657 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.9706. Min Act: -0.0001

Data Index: 869867 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.9556. Min Act: -0.0001

Data Index: 1127543 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.9650. Min Act: -0.0001

Data Index: 1232024 (C4 (Web Text))

Max Activating Token Index: 467