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

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

Neuron 3271 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.1563. Min Range: -2.1563

Max Act: 2.1563. Min Act: -0.0002

Data Index: 326585 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.9120. Min Act: -0.0002

Data Index: 735266 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.8532. Min Act: -0.0002

Data Index: 446290 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.8043. Min Act: -0.0002

Data Index: 52562 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.8781. Min Act: -0.0002

Data Index: 876064 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.8065. Min Act: -0.0002

Data Index: 522043 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.8143. Min Act: -0.0002

Data Index: 61401 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.8270. Min Act: -0.0002

Data Index: 910005 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.7739. Min Act: -0.0002

Data Index: 59570 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.7802. Min Act: -0.0002

Data Index: 629340 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.8290. Min Act: -0.0002

Data Index: 676415 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.8067. Min Act: -0.0002

Data Index: 357497 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.7479. Min Act: -0.0002

Data Index: 307796 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.7789. Min Act: -0.0002

Data Index: 72241 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.7549. Min Act: -0.0002

Data Index: 334780 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.7365. Min Act: -0.0002

Data Index: 533573 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.7444. Min Act: -0.0002

Data Index: 1164486 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.7145. Min Act: -0.0002

Data Index: 478141 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.6801. Min Act: -0.0003

Data Index: 666471 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 2.1563. Min Range: -2.1563

Max Act: 1.7008. Min Act: -0.0002

Data Index: 1003258 (C4 (Web Text))

Max Activating Token Index: 291