Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3481 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0503. Min Act: -0.0001

Data Index: 566111 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0456. Min Act: -0.0002

Data Index: 232590 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0437. Min Act: -0.0002

Data Index: 774103 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0448. Min Act: -0.0002

Data Index: 553064 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0444. Min Act: -0.0001

Data Index: 1543637 (Python Code)

Max Activating Token Index: 516

Text #5

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1142579 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0431. Min Act: -0.0001

Data Index: 929616 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0426. Min Act: -0.0002

Data Index: 396374 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0407. Min Act: -0.0001

Data Index: 591897 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0420. Min Act: -0.0002

Data Index: 968439 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1048333 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0421. Min Act: -0.0002

Data Index: 86966 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0433. Min Act: -0.0002

Data Index: 543867 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0407. Min Act: -0.0001

Data Index: 215953 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0415. Min Act: -0.0002

Data Index: 162808 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0408. Min Act: -0.0002

Data Index: 428200 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1091258 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0405. Min Act: -0.0001

Data Index: 470673 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0366. Min Act: -0.0002

Data Index: 256761 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0379. Min Act: -0.0002

Data Index: 82992 (C4 (Web Text))

Max Activating Token Index: 957