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

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

Neuron 3617 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.6608. Min Range: -8.6608

Max Act: 8.6038. Min Act: -0.0000

Data Index: 448996 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 8.6608. Min Range: -8.6608

Max Act: 8.3479. Min Act: -0.0000

Data Index: 1321598 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 8.6608. Min Range: -8.6608

Max Act: 8.6608. Min Act: -0.0000

Data Index: 276547 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 8.6608. Min Range: -8.6608

Max Act: 8.4390. Min Act: -0.0000

Data Index: 633297 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 8.6608. Min Range: -8.6608

Max Act: 8.3720. Min Act: -0.0000

Data Index: 232383 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 8.6608. Min Range: -8.6608

Max Act: 8.1487. Min Act: -0.0000

Data Index: 310755 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 8.6608. Min Range: -8.6608

Max Act: 8.3213. Min Act: -0.0000

Data Index: 1008666 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 8.6608. Min Range: -8.6608

Max Act: 7.6754. Min Act: -0.0000

Data Index: 898512 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 8.6608. Min Range: -8.6608

Max Act: 7.7974. Min Act: -0.0000

Data Index: 1085769 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 8.6608. Min Range: -8.6608

Max Act: 8.0728. Min Act: -0.0000

Data Index: 1352693 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 8.6608. Min Range: -8.6608

Max Act: 7.8107. Min Act: -0.0000

Data Index: 200910 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 8.6608. Min Range: -8.6608

Max Act: 7.6002. Min Act: -0.0000

Data Index: 251774 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 8.6608. Min Range: -8.6608

Max Act: 7.2732. Min Act: -0.0000

Data Index: 904216 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 8.6608. Min Range: -8.6608

Max Act: 7.3955. Min Act: -0.0000

Data Index: 627690 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 8.6608. Min Range: -8.6608

Max Act: 7.3029. Min Act: -0.0000

Data Index: 7745 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 8.6608. Min Range: -8.6608

Max Act: 6.3857. Min Act: -0.0000

Data Index: 874757 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 8.6608. Min Range: -8.6608

Max Act: 6.9298. Min Act: -0.0000

Data Index: 652439 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 8.6608. Min Range: -8.6608

Max Act: 7.2316. Min Act: -0.0000

Data Index: 728090 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 8.6608. Min Range: -8.6608

Max Act: 6.7045. Min Act: -0.0000

Data Index: 1109857 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 8.6608. Min Range: -8.6608

Max Act: 6.9581. Min Act: -0.0000

Data Index: 422069 (C4 (Web Text))

Max Activating Token Index: 789