Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5783 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1171844 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0441. Min Act: -0.0001

Data Index: 379375 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1010571 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0425. Min Act: -0.0001

Data Index: 1328739 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0420. Min Act: -0.0001

Data Index: 345209 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0425. Min Act: -0.0001

Data Index: 665825 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0417. Min Act: -0.0001

Data Index: 476504 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0427. Min Act: -0.0001

Data Index: 498307 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0424. Min Act: -0.0001

Data Index: 1073441 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0420. Min Act: -0.0001

Data Index: 765244 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0408. Min Act: -0.0001

Data Index: 793304 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0420. Min Act: -0.0001

Data Index: 413712 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0406. Min Act: -0.0001

Data Index: 855669 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0415. Min Act: -0.0001

Data Index: 878908 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0407. Min Act: -0.0001

Data Index: 609740 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0409. Min Act: -0.0001

Data Index: 338081 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0415. Min Act: -0.0001

Data Index: 1041012 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0404. Min Act: -0.0001

Data Index: 518692 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1072963 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0403. Min Act: -0.0001

Data Index: 895490 (C4 (Web Text))

Max Activating Token Index: 140