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

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

Neuron 623 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0461. Min Act: -0.0004

Data Index: 665325 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0453. Min Act: -0.0004

Data Index: 928991 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0400. Min Act: -0.0004

Data Index: 240651 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0381. Min Act: -0.0004

Data Index: 1351714 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0371. Min Act: -0.0004

Data Index: 1153429 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0368. Min Act: -0.0004

Data Index: 465370 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0363. Min Act: -0.0004

Data Index: 400146 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0362. Min Act: -0.0004

Data Index: 184812 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0362. Min Act: -0.0004

Data Index: 1076258 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0360. Min Act: -0.0004

Data Index: 2201 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0357. Min Act: -0.0004

Data Index: 354550 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0355. Min Act: -0.0004

Data Index: 636060 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0341. Min Act: -0.0004

Data Index: 611599 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0349. Min Act: -0.0004

Data Index: 1118829 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0355. Min Act: -0.0004

Data Index: 305450 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0345. Min Act: -0.0004

Data Index: 431890 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0341. Min Act: -0.0004

Data Index: 742678 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0349. Min Act: -0.0004

Data Index: 831913 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0353. Min Act: -0.0004

Data Index: 512847 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0338. Min Act: -0.0004

Data Index: 695169 (C4 (Web Text))

Max Activating Token Index: 358