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

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

Neuron 3257 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8485. Min Range: -2.8485

Max Act: 2.8485. Min Act: -0.0000

Data Index: 1585472 (Python Code)

Max Activating Token Index: 242

Text #1

Max Range: 2.8485. Min Range: -2.8485

Max Act: 2.6460. Min Act: -0.0000

Data Index: 1556536 (Python Code)

Max Activating Token Index: 512

Text #2

Max Range: 2.8485. Min Range: -2.8485

Max Act: 2.7292. Min Act: -0.0000

Data Index: 1417749 (Python Code)

Max Activating Token Index: 735

Text #3

Max Range: 2.8485. Min Range: -2.8485

Max Act: 2.6569. Min Act: -0.0000

Data Index: 1476949 (Python Code)

Max Activating Token Index: 765

Text #4

Max Range: 2.8485. Min Range: -2.8485

Max Act: 2.5825. Min Act: -0.0000

Data Index: 1369444 (Python Code)

Max Activating Token Index: 229

Text #5

Max Range: 2.8485. Min Range: -2.8485

Max Act: 2.5179. Min Act: 0.0000

Data Index: 1490806 (Python Code)

Max Activating Token Index: 641

Text #6

Max Range: 2.8485. Min Range: -2.8485

Max Act: 2.4762. Min Act: -0.0000

Data Index: 1578295 (Python Code)

Max Activating Token Index: 411

Text #7

Max Range: 2.8485. Min Range: -2.8485

Max Act: 2.4603. Min Act: -0.0000

Data Index: 1501151 (Python Code)

Max Activating Token Index: 394

Text #8

Max Range: 2.8485. Min Range: -2.8485

Max Act: 2.3773. Min Act: -0.0000

Data Index: 1609629 (Python Code)

Max Activating Token Index: 895

Text #9

Max Range: 2.8485. Min Range: -2.8485

Max Act: 2.5377. Min Act: -0.0000

Data Index: 1542479 (Python Code)

Max Activating Token Index: 354

Text #10

Max Range: 2.8485. Min Range: -2.8485

Max Act: 2.3616. Min Act: -0.0000

Data Index: 1609672 (Python Code)

Max Activating Token Index: 506

Text #11

Max Range: 2.8485. Min Range: -2.8485

Max Act: 2.3739. Min Act: -0.0000

Data Index: 1445122 (Python Code)

Max Activating Token Index: 718

Text #12

Max Range: 2.8485. Min Range: -2.8485

Max Act: 2.3548. Min Act: -0.0000

Data Index: 1479029 (Python Code)

Max Activating Token Index: 745

Text #13

Max Range: 2.8485. Min Range: -2.8485

Max Act: 2.3603. Min Act: -0.0000

Data Index: 1493202 (Python Code)

Max Activating Token Index: 324

Text #14

Max Range: 2.8485. Min Range: -2.8485

Max Act: 2.1436. Min Act: -0.0000

Data Index: 1584594 (Python Code)

Max Activating Token Index: 855

Text #15

Max Range: 2.8485. Min Range: -2.8485

Max Act: 2.4018. Min Act: -0.0000

Data Index: 1427272 (Python Code)

Max Activating Token Index: 902

Text #16

Max Range: 2.8485. Min Range: -2.8485

Max Act: 2.2781. Min Act: -0.0000

Data Index: 1461902 (Python Code)

Max Activating Token Index: 694

Text #17

Max Range: 2.8485. Min Range: -2.8485

Max Act: 2.2662. Min Act: -0.0000

Data Index: 1447771 (Python Code)

Max Activating Token Index: 218

Text #18

Max Range: 2.8485. Min Range: -2.8485

Max Act: 2.0863. Min Act: -0.0000

Data Index: 1593700 (Python Code)

Max Activating Token Index: 962

Text #19

Max Range: 2.8485. Min Range: -2.8485

Max Act: 2.2404. Min Act: -0.0000

Data Index: 1543285 (Python Code)

Max Activating Token Index: 814