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

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

Neuron 988 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: 0.8780. Min Range: -0.8780

Max Act: 0.8780. Min Act: -0.0000

Data Index: 186729 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.7516. Min Act: -0.0000

Data Index: 941975 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.7340. Min Act: -0.0000

Data Index: 432611 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.7568. Min Act: -0.0000

Data Index: 1319828 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.7050. Min Act: -0.0000

Data Index: 638638 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.7148. Min Act: -0.0000

Data Index: 256471 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.7086. Min Act: -0.0000

Data Index: 335195 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.7327. Min Act: -0.0000

Data Index: 476736 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.6853. Min Act: -0.0000

Data Index: 917999 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.6435. Min Act: -0.0000

Data Index: 618742 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.6531. Min Act: -0.0000

Data Index: 594140 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.6570. Min Act: -0.0000

Data Index: 57306 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.6781. Min Act: -0.0000

Data Index: 321563 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.6377. Min Act: -0.0000

Data Index: 695056 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1331864 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.6209. Min Act: -0.0000

Data Index: 555740 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.5891. Min Act: -0.0000

Data Index: 940396 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.5737. Min Act: -0.0000

Data Index: 681622 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.6119. Min Act: -0.0000

Data Index: 772305 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.8780. Min Range: -0.8780

Max Act: 0.6028. Min Act: -0.0000

Data Index: 1053829 (C4 (Web Text))

Max Activating Token Index: 283