Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2884 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.9814. Min Act: -0.0001

Data Index: 1296623 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.7249. Min Act: -0.0001

Data Index: 417075 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.6097. Min Act: -0.0001

Data Index: 206991 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.6424. Min Act: -0.0001

Data Index: 894009 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.5803. Min Act: -0.0001

Data Index: 1030371 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.6451. Min Act: -0.0001

Data Index: 780265 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.5765. Min Act: -0.0001

Data Index: 794759 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.5737. Min Act: -0.0000

Data Index: 1155142 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.5653. Min Act: -0.0001

Data Index: 2522 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.5704. Min Act: -0.0001

Data Index: 901572 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.5415. Min Act: -0.0001

Data Index: 102827 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.5729. Min Act: -0.0001

Data Index: 664952 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.4937. Min Act: -0.0001

Data Index: 411358 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.5204. Min Act: -0.0001

Data Index: 1005191 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.5008. Min Act: -0.0000

Data Index: 966922 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.5157. Min Act: -0.0001

Data Index: 65912 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.5115. Min Act: -0.0001

Data Index: 1063114 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.4881. Min Act: -0.0001

Data Index: 795852 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.5036. Min Act: -0.0001

Data Index: 346455 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.4688. Min Act: -0.0001

Data Index: 434087 (C4 (Web Text))

Max Activating Token Index: 494