Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1356 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0566. Min Act: -0.0006

Data Index: 989774 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0505. Min Act: -0.0006

Data Index: 799481 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0460. Min Act: -0.0006

Data Index: 310578 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0550. Min Act: -0.0006

Data Index: 223467 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0469. Min Act: -0.0006

Data Index: 1078507 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0477. Min Act: -0.0006

Data Index: 855964 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0473. Min Act: -0.0006

Data Index: 1147054 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0462. Min Act: -0.0006

Data Index: 680189 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0424. Min Act: -0.0006

Data Index: 1057441 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0476. Min Act: -0.0006

Data Index: 843202 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0464. Min Act: -0.0006

Data Index: 1344280 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0414. Min Act: -0.0006

Data Index: 360104 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0423. Min Act: -0.0006

Data Index: 1615701 (Python Code)

Max Activating Token Index: 492

Text #13

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0419. Min Act: -0.0006

Data Index: 285753 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0454. Min Act: -0.0006

Data Index: 318003 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0455. Min Act: -0.0006

Data Index: 684853 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0443. Min Act: -0.0006

Data Index: 182787 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0514. Min Act: -0.0006

Data Index: 46953 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0429. Min Act: -0.0006

Data Index: 1110311 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0436. Min Act: -0.0006

Data Index: 201131 (C4 (Web Text))

Max Activating Token Index: 789