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

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

Neuron 1035 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: 3.8244. Min Range: -3.8244

Max Act: 3.8244. Min Act: -0.0001

Data Index: 642528 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.7660. Min Act: -0.0001

Data Index: 785822 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.5198. Min Act: -0.0001

Data Index: 975059 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.4381. Min Act: -0.0001

Data Index: 844542 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.1328. Min Act: -0.0001

Data Index: 548449 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.5218. Min Act: -0.0001

Data Index: 831561 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.4359. Min Act: -0.0001

Data Index: 1194229 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.4128. Min Act: -0.0001

Data Index: 159523 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.2591. Min Act: -0.0001

Data Index: 274678 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.2203. Min Act: -0.0001

Data Index: 704093 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.1767. Min Act: -0.0001

Data Index: 860595 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.0704. Min Act: -0.0001

Data Index: 836870 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.3203. Min Act: -0.0001

Data Index: 981597 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 3.8244. Min Range: -3.8244

Max Act: 2.9052. Min Act: -0.0001

Data Index: 804975 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.1589. Min Act: -0.0001

Data Index: 576583 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 3.8244. Min Range: -3.8244

Max Act: 2.8709. Min Act: -0.0001

Data Index: 1027486 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.2727. Min Act: -0.0001

Data Index: 1307952 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.1342. Min Act: -0.0001

Data Index: 1084118 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 3.8244. Min Range: -3.8244

Max Act: 2.8487. Min Act: -0.0001

Data Index: 798562 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.0957. Min Act: -0.0001

Data Index: 1080596 (C4 (Web Text))

Max Activating Token Index: 525