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

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

Neuron 6015 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0783. Min Act: -0.0001

Data Index: 494212 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0807. Min Act: -0.0001

Data Index: 280561 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0642. Min Act: -0.0001

Data Index: 959508 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0699. Min Act: -0.0001

Data Index: 1003676 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0713. Min Act: -0.0001

Data Index: 268234 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0685. Min Act: -0.0001

Data Index: 1105610 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0695. Min Act: -0.0001

Data Index: 337082 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0629. Min Act: -0.0001

Data Index: 489020 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0687. Min Act: -0.0001

Data Index: 649336 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1083404 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0594. Min Act: -0.0001

Data Index: 151086 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1294127 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1016881 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0600. Min Act: -0.0001

Data Index: 847883 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0522. Min Act: -0.0001

Data Index: 1341856 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0472. Min Act: -0.0002

Data Index: 996609 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0537. Min Act: -0.0002

Data Index: 405607 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0580. Min Act: -0.0001

Data Index: 33919 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0503. Min Act: -0.0001

Data Index: 112541 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0505. Min Act: -0.0001

Data Index: 1202335 (C4 (Web Text))

Max Activating Token Index: 187