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

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

Neuron 5258 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1987. Min Act: -0.0001

Data Index: 369698 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1348. Min Act: -0.0001

Data Index: 1072604 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1557. Min Act: -0.0001

Data Index: 1202834 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1616. Min Act: -0.0001

Data Index: 1046159 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1281. Min Act: -0.0002

Data Index: 839512 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1557. Min Act: -0.0001

Data Index: 1118723 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1394. Min Act: -0.0001

Data Index: 114901 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1479. Min Act: -0.0001

Data Index: 803459 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1380. Min Act: -0.0001

Data Index: 984269 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1365. Min Act: -0.0001

Data Index: 88823 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1502. Min Act: -0.0001

Data Index: 939276 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1427. Min Act: -0.0001

Data Index: 671165 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1281. Min Act: -0.0001

Data Index: 1171582 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1388. Min Act: -0.0001

Data Index: 477901 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1191. Min Act: -0.0001

Data Index: 1017065 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1533. Min Act: -0.0001

Data Index: 754203 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1260. Min Act: -0.0001

Data Index: 359538 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1245. Min Act: -0.0001

Data Index: 1013474 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1431. Min Act: -0.0001

Data Index: 682923 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1540. Min Act: -0.0001

Data Index: 1023275 (C4 (Web Text))

Max Activating Token Index: 934