Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3543 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1177446 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.4077. Min Act: -0.0000

Data Index: 521113 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3860. Min Act: 0.0000

Data Index: 862539 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.4036. Min Act: -0.0000

Data Index: 327891 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3870. Min Act: -0.0000

Data Index: 461323 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3761. Min Act: -0.0000

Data Index: 366636 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3891. Min Act: -0.0000

Data Index: 1132782 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3603. Min Act: -0.0000

Data Index: 14554 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3723. Min Act: -0.0000

Data Index: 591159 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3571. Min Act: -0.0000

Data Index: 149429 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3458. Min Act: -0.0000

Data Index: 344882 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3168. Min Act: -0.0000

Data Index: 143534 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3671. Min Act: -0.0000

Data Index: 348831 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3412. Min Act: -0.0000

Data Index: 1184902 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3425. Min Act: -0.0000

Data Index: 542352 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3526. Min Act: -0.0000

Data Index: 868918 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3293. Min Act: -0.0000

Data Index: 377450 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3480. Min Act: -0.0000

Data Index: 1274495 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3467. Min Act: -0.0000

Data Index: 399915 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3374. Min Act: -0.0000

Data Index: 1258424 (C4 (Web Text))

Max Activating Token Index: 631