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

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

Neuron 656 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.2802. Min Act: -0.0001

Data Index: 766764 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 3.2802. Min Range: -3.2802

Max Act: 3.0983. Min Act: -0.0001

Data Index: 741892 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.9514. Min Act: -0.0000

Data Index: 300865 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.6300. Min Act: -0.0001

Data Index: 1136902 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.8467. Min Act: -0.0000

Data Index: 1039155 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.6513. Min Act: -0.0000

Data Index: 239748 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.8665. Min Act: -0.0000

Data Index: 52719 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.6565. Min Act: -0.0001

Data Index: 1199487 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.2601. Min Act: -0.0001

Data Index: 930706 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.4113. Min Act: -0.0001

Data Index: 252736 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.3696. Min Act: -0.0000

Data Index: 1176581 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.3151. Min Act: -0.0000

Data Index: 725033 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.3793. Min Act: -0.0001

Data Index: 121731 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.1582. Min Act: -0.0000

Data Index: 726363 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.2381. Min Act: -0.0001

Data Index: 809655 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.3441. Min Act: -0.0000

Data Index: 953191 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.2433. Min Act: -0.0000

Data Index: 505386 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 3.2802. Min Range: -3.2802

Max Act: 2.1081. Min Act: -0.0000

Data Index: 344055 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 3.2802. Min Range: -3.2802

Max Act: 1.9803. Min Act: -0.0000

Data Index: 490059 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 3.2802. Min Range: -3.2802

Max Act: 1.9789. Min Act: -0.0001

Data Index: 1118005 (C4 (Web Text))

Max Activating Token Index: 38