Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 793 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1557. Min Act: -0.0000

Data Index: 735615 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1754. Min Act: -0.0001

Data Index: 1328245 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1542. Min Act: -0.0001

Data Index: 709117 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1532. Min Act: -0.0001

Data Index: 553005 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1407. Min Act: -0.0001

Data Index: 1095389 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1370. Min Act: -0.0001

Data Index: 428588 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1297. Min Act: -0.0001

Data Index: 403661 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1029179 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1320. Min Act: -0.0001

Data Index: 1101040 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1202. Min Act: -0.0000

Data Index: 990874 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1369. Min Act: -0.0001

Data Index: 822788 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1263. Min Act: -0.0001

Data Index: 1151291 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1417. Min Act: -0.0001

Data Index: 855375 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1362. Min Act: -0.0001

Data Index: 387514 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1140325 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1307. Min Act: -0.0001

Data Index: 1081917 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1288. Min Act: -0.0001

Data Index: 1287271 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1108. Min Act: -0.0001

Data Index: 58268 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1243. Min Act: -0.0000

Data Index: 781913 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1227. Min Act: -0.0001

Data Index: 1149797 (C4 (Web Text))

Max Activating Token Index: 224