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

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

Neuron 1540 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8414. Min Range: -2.8414

Max Act: 2.8414. Min Act: -0.0000

Data Index: 1332170 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 2.8414. Min Range: -2.8414

Max Act: 2.3761. Min Act: -0.0000

Data Index: 610729 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 2.8414. Min Range: -2.8414

Max Act: 2.4055. Min Act: -0.0000

Data Index: 800208 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 2.8414. Min Range: -2.8414

Max Act: 2.5347. Min Act: -0.0000

Data Index: 33823 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 2.8414. Min Range: -2.8414

Max Act: 2.3719. Min Act: -0.0000

Data Index: 458112 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 2.8414. Min Range: -2.8414

Max Act: 2.6454. Min Act: -0.0000

Data Index: 392090 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 2.8414. Min Range: -2.8414

Max Act: 2.5813. Min Act: -0.0000

Data Index: 646629 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 2.8414. Min Range: -2.8414

Max Act: 2.3963. Min Act: -0.0000

Data Index: 154581 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 2.8414. Min Range: -2.8414

Max Act: 2.0713. Min Act: -0.0000

Data Index: 599398 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 2.8414. Min Range: -2.8414

Max Act: 2.2232. Min Act: -0.0000

Data Index: 1039413 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 2.8414. Min Range: -2.8414

Max Act: 2.0397. Min Act: -0.0000

Data Index: 439949 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 2.8414. Min Range: -2.8414

Max Act: 2.0405. Min Act: -0.0000

Data Index: 1117902 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 2.8414. Min Range: -2.8414

Max Act: 2.0316. Min Act: -0.0000

Data Index: 1122892 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 2.8414. Min Range: -2.8414

Max Act: 2.0108. Min Act: -0.0000

Data Index: 1352339 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 2.8414. Min Range: -2.8414

Max Act: 1.9729. Min Act: -0.0000

Data Index: 402668 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 2.8414. Min Range: -2.8414

Max Act: 1.9705. Min Act: -0.0000

Data Index: 244875 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 2.8414. Min Range: -2.8414

Max Act: 1.9115. Min Act: -0.0000

Data Index: 53696 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 2.8414. Min Range: -2.8414

Max Act: 1.9004. Min Act: -0.0000

Data Index: 39879 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 2.8414. Min Range: -2.8414

Max Act: 1.9992. Min Act: -0.0000

Data Index: 1209199 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 2.8414. Min Range: -2.8414

Max Act: 1.9389. Min Act: -0.0000

Data Index: 1150229 (C4 (Web Text))

Max Activating Token Index: 486