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

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

Neuron 3278 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.1488. Min Act: -0.0000

Data Index: 504455 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.1580. Min Act: -0.0000

Data Index: 1344552 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.0180. Min Act: -0.0000

Data Index: 1112208 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.0417. Min Act: -0.0000

Data Index: 732230 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.0275. Min Act: -0.0000

Data Index: 754833 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.0811. Min Act: -0.0000

Data Index: 8844 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.0293. Min Act: -0.0000

Data Index: 218272 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9426. Min Act: -0.0000

Data Index: 731695 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9970. Min Act: -0.0000

Data Index: 574560 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9451. Min Act: -0.0000

Data Index: 462248 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9521. Min Act: -0.0000

Data Index: 1164964 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8662. Min Act: -0.0000

Data Index: 585014 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9439. Min Act: -0.0000

Data Index: 539829 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8612. Min Act: -0.0000

Data Index: 1329347 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9381. Min Act: -0.0000

Data Index: 639481 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9290. Min Act: -0.0000

Data Index: 712617 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.7767. Min Act: -0.0000

Data Index: 646297 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8249. Min Act: -0.0000

Data Index: 1023334 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8900. Min Act: -0.0000

Data Index: 983034 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8256. Min Act: -0.0000

Data Index: 1242346 (C4 (Web Text))

Max Activating Token Index: 134