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

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

Neuron 4959 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: 1.2630. Min Range: -1.2630

Max Act: 1.1442. Min Act: -0.0000

Data Index: 115735 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 1.2630. Min Range: -1.2630

Max Act: 1.2630. Min Act: -0.0000

Data Index: 1346494 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 1.2630. Min Range: -1.2630

Max Act: 1.1263. Min Act: -0.0000

Data Index: 398802 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.9988. Min Act: -0.0000

Data Index: 1117126 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 1.2630. Min Range: -1.2630

Max Act: 1.0184. Min Act: -0.0000

Data Index: 352557 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.9097. Min Act: -0.0000

Data Index: 1151165 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.9038. Min Act: -0.0000

Data Index: 686150 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.8742. Min Act: -0.0000

Data Index: 660835 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.8717. Min Act: -0.0000

Data Index: 693023 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.8164. Min Act: -0.0000

Data Index: 682391 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.8874. Min Act: -0.0000

Data Index: 108256 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.7310. Min Act: -0.0000

Data Index: 518568 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.7976. Min Act: -0.0000

Data Index: 156373 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.8139. Min Act: -0.0000

Data Index: 448550 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.8310. Min Act: -0.0000

Data Index: 788846 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.7578. Min Act: -0.0000

Data Index: 225520 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.7592. Min Act: -0.0000

Data Index: 544942 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.7366. Min Act: -0.0000

Data Index: 127113 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1301347 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.7478. Min Act: -0.0000

Data Index: 228268 (C4 (Web Text))

Max Activating Token Index: 859