Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2499 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.3807. Min Act: -0.0001

Data Index: 572608 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.3782. Min Act: -0.0001

Data Index: 1183078 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.3268. Min Act: -0.0001

Data Index: 1189318 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.2979. Min Act: -0.0001

Data Index: 319813 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.3016. Min Act: -0.0001

Data Index: 1338202 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.2891. Min Act: -0.0001

Data Index: 337938 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.2649. Min Act: -0.0001

Data Index: 959482 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.2509. Min Act: -0.0001

Data Index: 893708 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.2557. Min Act: -0.0001

Data Index: 1276769 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.2446. Min Act: -0.0001

Data Index: 928670 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.2549. Min Act: -0.0001

Data Index: 391962 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.2372. Min Act: -0.0001

Data Index: 620837 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.2361. Min Act: -0.0001

Data Index: 94559 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.2509. Min Act: -0.0002

Data Index: 740902 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.2182. Min Act: -0.0001

Data Index: 72636 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.2331. Min Act: -0.0001

Data Index: 316782 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.2040. Min Act: -0.0001

Data Index: 1280569 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.2089. Min Act: -0.0001

Data Index: 981295 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.2189. Min Act: -0.0001

Data Index: 947744 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 0.3807. Min Range: -0.3807

Max Act: 0.2149. Min Act: -0.0001

Data Index: 193198 (C4 (Web Text))

Max Activating Token Index: 527