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

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

Neuron 6105 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1155712 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4798. Min Act: -0.0000

Data Index: 1054462 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4532. Min Act: -0.0000

Data Index: 855014 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.3839. Min Act: -0.0000

Data Index: 147464 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.3798. Min Act: -0.0000

Data Index: 546007 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1138073 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.3475. Min Act: -0.0000

Data Index: 425753 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.3353. Min Act: -0.0000

Data Index: 874371 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1166900 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.3066. Min Act: -0.0000

Data Index: 577155 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.3112. Min Act: -0.0000

Data Index: 505242 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.2880. Min Act: -0.0000

Data Index: 196395 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.3001. Min Act: -0.0000

Data Index: 321642 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.3310. Min Act: -0.0000

Data Index: 754888 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.2717. Min Act: -0.0000

Data Index: 700937 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.2866. Min Act: -0.0000

Data Index: 1086358 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.2932. Min Act: -0.0000

Data Index: 404779 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.2569. Min Act: -0.0000

Data Index: 428331 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.3030. Min Act: -0.0000

Data Index: 1298493 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1015836 (C4 (Web Text))

Max Activating Token Index: 699