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

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

Neuron 734 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2921. Min Act: -0.0001

Data Index: 53434 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2872. Min Act: -0.0000

Data Index: 969475 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2882. Min Act: -0.0001

Data Index: 632273 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2856. Min Act: -0.0000

Data Index: 827323 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1284750 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2728. Min Act: -0.0001

Data Index: 119944 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2565. Min Act: -0.0001

Data Index: 1075434 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2459. Min Act: -0.0001

Data Index: 861744 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2503. Min Act: -0.0001

Data Index: 174438 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2500. Min Act: -0.0001

Data Index: 618313 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2548. Min Act: -0.0001

Data Index: 1310820 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2348. Min Act: -0.0001

Data Index: 789670 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2482. Min Act: -0.0000

Data Index: 416100 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2376. Min Act: -0.0001

Data Index: 890538 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2458. Min Act: -0.0001

Data Index: 385548 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2430. Min Act: -0.0000

Data Index: 243141 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2431. Min Act: -0.0001

Data Index: 1004342 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2351. Min Act: -0.0001

Data Index: 582700 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2371. Min Act: -0.0000

Data Index: 629296 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2381. Min Act: -0.0000

Data Index: 72701 (C4 (Web Text))

Max Activating Token Index: 486