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

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

Neuron 5574 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5617. Min Range: -2.5617

Max Act: 2.5617. Min Act: -0.0000

Data Index: 123352 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 2.5617. Min Range: -2.5617

Max Act: 2.2223. Min Act: -0.0000

Data Index: 794632 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 2.5617. Min Range: -2.5617

Max Act: 2.1568. Min Act: -0.0000

Data Index: 1356125 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 2.5617. Min Range: -2.5617

Max Act: 2.1517. Min Act: -0.0000

Data Index: 763001 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 2.5617. Min Range: -2.5617

Max Act: 2.1423. Min Act: -0.0000

Data Index: 1017514 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 2.5617. Min Range: -2.5617

Max Act: 2.2543. Min Act: -0.0000

Data Index: 803831 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 2.5617. Min Range: -2.5617

Max Act: 2.0304. Min Act: -0.0000

Data Index: 593270 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 2.5617. Min Range: -2.5617

Max Act: 1.9599. Min Act: -0.0000

Data Index: 455189 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 2.5617. Min Range: -2.5617

Max Act: 2.0405. Min Act: -0.0000

Data Index: 711581 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 2.5617. Min Range: -2.5617

Max Act: 2.0309. Min Act: -0.0000

Data Index: 947735 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 2.5617. Min Range: -2.5617

Max Act: 1.9873. Min Act: -0.0000

Data Index: 752968 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 2.5617. Min Range: -2.5617

Max Act: 1.8700. Min Act: -0.0000

Data Index: 298701 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 2.5617. Min Range: -2.5617

Max Act: 2.0521. Min Act: -0.0000

Data Index: 166432 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 2.5617. Min Range: -2.5617

Max Act: 1.9698. Min Act: -0.0000

Data Index: 796780 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 2.5617. Min Range: -2.5617

Max Act: 1.9742. Min Act: -0.0000

Data Index: 683978 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 2.5617. Min Range: -2.5617

Max Act: 1.8412. Min Act: -0.0000

Data Index: 605594 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 2.5617. Min Range: -2.5617

Max Act: 1.8406. Min Act: -0.0000

Data Index: 202205 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 2.5617. Min Range: -2.5617

Max Act: 1.8480. Min Act: -0.0000

Data Index: 965050 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 2.5617. Min Range: -2.5617

Max Act: 1.7157. Min Act: -0.0000

Data Index: 1176309 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 2.5617. Min Range: -2.5617

Max Act: 1.8177. Min Act: -0.0000

Data Index: 824778 (C4 (Web Text))

Max Activating Token Index: 971