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

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

Neuron 4249 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1096214 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4430. Min Act: -0.0000

Data Index: 782779 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1131254 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4039. Min Act: -0.0000

Data Index: 644772 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4413. Min Act: -0.0000

Data Index: 890169 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4132. Min Act: -0.0000

Data Index: 219723 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4201. Min Act: -0.0000

Data Index: 238425 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.3834. Min Act: -0.0000

Data Index: 28981 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.3927. Min Act: -0.0000

Data Index: 1284222 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1159204 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4147. Min Act: -0.0000

Data Index: 1144485 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.3872. Min Act: -0.0000

Data Index: 727106 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.3797. Min Act: -0.0000

Data Index: 701033 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.3752. Min Act: -0.0000

Data Index: 489348 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.3636. Min Act: -0.0000

Data Index: 787210 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.3827. Min Act: -0.0000

Data Index: 59435 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.3693. Min Act: -0.0000

Data Index: 1159645 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.3675. Min Act: -0.0000

Data Index: 499040 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.3508. Min Act: -0.0000

Data Index: 538052 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.3753. Min Act: -0.0000

Data Index: 651988 (C4 (Web Text))

Max Activating Token Index: 133