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

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

Neuron 1363 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: 2.0752. Min Range: -2.0752

Max Act: 2.0752. Min Act: -0.0000

Data Index: 542940 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.6218. Min Act: -0.0000

Data Index: 192562 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.8936. Min Act: -0.0000

Data Index: 1345060 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.9126. Min Act: -0.0000

Data Index: 674912 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.6409. Min Act: -0.0000

Data Index: 625142 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.3562. Min Act: -0.0000

Data Index: 683611 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.1849. Min Act: -0.0000

Data Index: 665172 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.2312. Min Act: -0.0000

Data Index: 1054352 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.0747. Min Act: -0.0000

Data Index: 518675 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.0415. Min Act: -0.0000

Data Index: 57741 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 2.0752. Min Range: -2.0752

Max Act: 0.9803. Min Act: -0.0000

Data Index: 1319462 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 2.0752. Min Range: -2.0752

Max Act: 1.1183. Min Act: -0.0000

Data Index: 528452 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 2.0752. Min Range: -2.0752

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1107038 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 2.0752. Min Range: -2.0752

Max Act: 0.9842. Min Act: -0.0000

Data Index: 762275 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 2.0752. Min Range: -2.0752

Max Act: 0.9761. Min Act: -0.0000

Data Index: 1141878 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 2.0752. Min Range: -2.0752

Max Act: 0.8821. Min Act: -0.0000

Data Index: 699502 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 2.0752. Min Range: -2.0752

Max Act: 0.9995. Min Act: -0.0000

Data Index: 710753 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 2.0752. Min Range: -2.0752

Max Act: 0.8507. Min Act: -0.0000

Data Index: 577577 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 2.0752. Min Range: -2.0752

Max Act: 0.8679. Min Act: -0.0000

Data Index: 718171 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 2.0752. Min Range: -2.0752

Max Act: 0.8338. Min Act: -0.0000

Data Index: 482445 (C4 (Web Text))

Max Activating Token Index: 586