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

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

Neuron 3994 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3705. Min Act: -0.0002

Data Index: 1080188 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.4055. Min Act: -0.0002

Data Index: 671904 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3614. Min Act: -0.0002

Data Index: 1195313 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3824. Min Act: -0.0002

Data Index: 825856 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3904. Min Act: -0.0002

Data Index: 1017871 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3538. Min Act: -0.0002

Data Index: 690386 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3622. Min Act: -0.0002

Data Index: 310021 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3687. Min Act: -0.0002

Data Index: 466967 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3437. Min Act: -0.0002

Data Index: 1068162 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3421. Min Act: -0.0002

Data Index: 745860 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3488. Min Act: -0.0002

Data Index: 618542 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3992. Min Act: -0.0002

Data Index: 544443 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3470. Min Act: -0.0002

Data Index: 458071 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3223. Min Act: -0.0002

Data Index: 5154 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3399. Min Act: -0.0002

Data Index: 933041 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3862. Min Act: -0.0002

Data Index: 517068 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3269. Min Act: -0.0002

Data Index: 1619799 (Python Code)

Max Activating Token Index: 947

Text #17

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3205. Min Act: -0.0002

Data Index: 1296797 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3087. Min Act: -0.0002

Data Index: 192742 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3343. Min Act: -0.0002

Data Index: 1160127 (C4 (Web Text))

Max Activating Token Index: 569