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

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

Neuron 2197 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.5377. Min Act: -0.0001

Data Index: 1565808 (Python Code)

Max Activating Token Index: 1017

Text #1

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4390. Min Act: -0.0001

Data Index: 1432679 (Python Code)

Max Activating Token Index: 868

Text #2

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.5380. Min Act: -0.0001

Data Index: 1437620 (Python Code)

Max Activating Token Index: 404

Text #3

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4575. Min Act: -0.0001

Data Index: 1655443 (Python Code)

Max Activating Token Index: 817

Text #4

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4871. Min Act: -0.0001

Data Index: 1565146 (Python Code)

Max Activating Token Index: 729

Text #5

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4726. Min Act: -0.0001

Data Index: 1458325 (Python Code)

Max Activating Token Index: 868

Text #6

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4326. Min Act: -0.0001

Data Index: 1407456 (Python Code)

Max Activating Token Index: 934

Text #7

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4720. Min Act: -0.0001

Data Index: 1603597 (Python Code)

Max Activating Token Index: 889

Text #8

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4229. Min Act: -0.0001

Data Index: 1388634 (Python Code)

Max Activating Token Index: 607

Text #9

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.3970. Min Act: -0.0001

Data Index: 1432353 (Python Code)

Max Activating Token Index: 632

Text #10

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4444. Min Act: -0.0001

Data Index: 1387788 (Python Code)

Max Activating Token Index: 868

Text #11

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4456. Min Act: -0.0001

Data Index: 1492102 (Python Code)

Max Activating Token Index: 1006

Text #12

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4409. Min Act: -0.0001

Data Index: 1620550 (Python Code)

Max Activating Token Index: 927

Text #13

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.3994. Min Act: -0.0001

Data Index: 1501278 (Python Code)

Max Activating Token Index: 650

Text #14

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.3831. Min Act: -0.0001

Data Index: 1385139 (Python Code)

Max Activating Token Index: 635

Text #15

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4104. Min Act: -0.0001

Data Index: 1451865 (Python Code)

Max Activating Token Index: 929

Text #16

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4345. Min Act: -0.0001

Data Index: 1451064 (Python Code)

Max Activating Token Index: 553

Text #17

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4336. Min Act: -0.0001

Data Index: 1637170 (Python Code)

Max Activating Token Index: 541

Text #18

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4197. Min Act: -0.0001

Data Index: 1370984 (Python Code)

Max Activating Token Index: 1014

Text #19

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4260. Min Act: -0.0001

Data Index: 1482993 (Python Code)

Max Activating Token Index: 794