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

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

Neuron 5702 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: 0.0640. Min Range: -0.0640

Max Act: 0.0640. Min Act: -0.0001

Data Index: 828074 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0578. Min Act: -0.0001

Data Index: 1349180 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0510. Min Act: -0.0001

Data Index: 1165594 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0495. Min Act: -0.0001

Data Index: 768236 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0487. Min Act: -0.0001

Data Index: 1129986 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0463. Min Act: -0.0001

Data Index: 697443 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0455. Min Act: -0.0001

Data Index: 1350902 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0444. Min Act: -0.0001

Data Index: 636483 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1185941 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0413. Min Act: -0.0001

Data Index: 874742 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0420. Min Act: -0.0001

Data Index: 1200296 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0411. Min Act: -0.0001

Data Index: 1224484 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0417. Min Act: -0.0001

Data Index: 776507 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0406. Min Act: -0.0001

Data Index: 326447 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0407. Min Act: -0.0001

Data Index: 1293394 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0396. Min Act: -0.0001

Data Index: 946901 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0402. Min Act: -0.0001

Data Index: 504268 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0406. Min Act: -0.0001

Data Index: 127971 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0395. Min Act: -0.0001

Data Index: 43108 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0383. Min Act: -0.0001

Data Index: 486078 (C4 (Web Text))

Max Activating Token Index: 587