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

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

Neuron 4829 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0593. Min Act: -0.0000

Data Index: 894932 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0534. Min Act: -0.0000

Data Index: 1126927 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0436. Min Act: -0.0000

Data Index: 362153 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0439. Min Act: -0.0000

Data Index: 674988 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0403. Min Act: -0.0000

Data Index: 1332298 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0454. Min Act: -0.0000

Data Index: 1631189 (Python Code)

Max Activating Token Index: 613

Text #6

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0409. Min Act: -0.0000

Data Index: 1149439 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0402. Min Act: -0.0000

Data Index: 1301556 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0390. Min Act: -0.0000

Data Index: 193322 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0419. Min Act: -0.0000

Data Index: 1207153 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0414. Min Act: 0.0000

Data Index: 185998 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0414. Min Act: -0.0000

Data Index: 886274 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0380. Min Act: -0.0000

Data Index: 4466 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0392. Min Act: -0.0000

Data Index: 40631 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0360. Min Act: -0.0000

Data Index: 866048 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0386. Min Act: -0.0000

Data Index: 714184 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0384. Min Act: -0.0000

Data Index: 1551016 (Python Code)

Max Activating Token Index: 1008

Text #17

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0380. Min Act: -0.0000

Data Index: 889633 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0377. Min Act: -0.0000

Data Index: 216183 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0374. Min Act: -0.0000

Data Index: 1400728 (Python Code)

Max Activating Token Index: 307