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

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

Neuron 5403 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3982. Min Range: -1.3982

Max Act: 1.3982. Min Act: -0.0000

Data Index: 457914 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 1.3982. Min Range: -1.3982

Max Act: 1.3273. Min Act: -0.0000

Data Index: 542122 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 1.3982. Min Range: -1.3982

Max Act: 1.2339. Min Act: -0.0000

Data Index: 677253 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 1.3982. Min Range: -1.3982

Max Act: 1.3547. Min Act: -0.0000

Data Index: 9060 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 1.3982. Min Range: -1.3982

Max Act: 1.2880. Min Act: -0.0001

Data Index: 401837 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 1.3982. Min Range: -1.3982

Max Act: 1.2245. Min Act: -0.0000

Data Index: 713863 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 1.3982. Min Range: -1.3982

Max Act: 1.2238. Min Act: -0.0000

Data Index: 614006 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 1.3982. Min Range: -1.3982

Max Act: 1.1174. Min Act: -0.0000

Data Index: 1181439 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 1.3982. Min Range: -1.3982

Max Act: 1.2238. Min Act: -0.0000

Data Index: 638539 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 1.3982. Min Range: -1.3982

Max Act: 1.2029. Min Act: -0.0000

Data Index: 461573 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 1.3982. Min Range: -1.3982

Max Act: 1.1699. Min Act: -0.0000

Data Index: 1351474 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 1.3982. Min Range: -1.3982

Max Act: 1.1928. Min Act: -0.0000

Data Index: 548730 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 1.3982. Min Range: -1.3982

Max Act: 1.1001. Min Act: -0.0000

Data Index: 473204 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 1.3982. Min Range: -1.3982

Max Act: 1.1257. Min Act: -0.0000

Data Index: 329200 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 1.3982. Min Range: -1.3982

Max Act: 1.1505. Min Act: -0.0000

Data Index: 739691 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 1.3982. Min Range: -1.3982

Max Act: 1.0971. Min Act: -0.0000

Data Index: 696378 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 1.3982. Min Range: -1.3982

Max Act: 1.2165. Min Act: -0.0000

Data Index: 350611 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 1.3982. Min Range: -1.3982

Max Act: 0.8656. Min Act: -0.0000

Data Index: 1006561 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 1.3982. Min Range: -1.3982

Max Act: 1.0987. Min Act: -0.0000

Data Index: 1003688 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 1.3982. Min Range: -1.3982

Max Act: 1.0834. Min Act: -0.0000

Data Index: 774782 (C4 (Web Text))

Max Activating Token Index: 391