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

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

Neuron 620 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4111. Min Range: -0.4111

Max Act: 0.4111. Min Act: -0.0003

Data Index: 208081 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.4111. Min Range: -0.4111

Max Act: 0.3526. Min Act: -0.0002

Data Index: 899443 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 0.4111. Min Range: -0.4111

Max Act: 0.3423. Min Act: -0.0002

Data Index: 1294394 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.4111. Min Range: -0.4111

Max Act: 0.3398. Min Act: -0.0003

Data Index: 719746 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 0.4111. Min Range: -0.4111

Max Act: 0.3311. Min Act: -0.0003

Data Index: 1349727 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.4111. Min Range: -0.4111

Max Act: 0.3094. Min Act: -0.0003

Data Index: 190686 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.4111. Min Range: -0.4111

Max Act: 0.2969. Min Act: -0.0003

Data Index: 885973 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.4111. Min Range: -0.4111

Max Act: 0.3041. Min Act: -0.0003

Data Index: 178567 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.4111. Min Range: -0.4111

Max Act: 0.3015. Min Act: -0.0003

Data Index: 557049 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.4111. Min Range: -0.4111

Max Act: 0.3000. Min Act: -0.0003

Data Index: 595407 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.4111. Min Range: -0.4111

Max Act: 0.2933. Min Act: -0.0003

Data Index: 882547 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.4111. Min Range: -0.4111

Max Act: 0.2852. Min Act: -0.0003

Data Index: 1344 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.4111. Min Range: -0.4111

Max Act: 0.2818. Min Act: -0.0003

Data Index: 828820 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.4111. Min Range: -0.4111

Max Act: 0.2795. Min Act: -0.0003

Data Index: 888326 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.4111. Min Range: -0.4111

Max Act: 0.2774. Min Act: -0.0003

Data Index: 706532 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.4111. Min Range: -0.4111

Max Act: 0.2774. Min Act: -0.0003

Data Index: 350983 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 0.4111. Min Range: -0.4111

Max Act: 0.2752. Min Act: -0.0003

Data Index: 1263248 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.4111. Min Range: -0.4111

Max Act: 0.2688. Min Act: -0.0003

Data Index: 1082513 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.4111. Min Range: -0.4111

Max Act: 0.2680. Min Act: -0.0003

Data Index: 888704 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.4111. Min Range: -0.4111

Max Act: 0.2773. Min Act: -0.0003

Data Index: 316976 (C4 (Web Text))

Max Activating Token Index: 167