Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1613 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1407. Min Act: -0.0002

Data Index: 1368412 (Python Code)

Max Activating Token Index: 968

Text #1

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1204. Min Act: -0.0003

Data Index: 919090 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1236. Min Act: -0.0002

Data Index: 1533839 (Python Code)

Max Activating Token Index: 143

Text #3

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1250. Min Act: -0.0002

Data Index: 1610130 (Python Code)

Max Activating Token Index: 1019

Text #4

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1095. Min Act: -0.0003

Data Index: 1595659 (Python Code)

Max Activating Token Index: 32

Text #5

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0928. Min Act: -0.0003

Data Index: 27370 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0991. Min Act: -0.0003

Data Index: 1647089 (Python Code)

Max Activating Token Index: 675

Text #7

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1019. Min Act: -0.0003

Data Index: 1260808 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1003. Min Act: -0.0003

Data Index: 1504280 (Python Code)

Max Activating Token Index: 103

Text #9

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0967. Min Act: -0.0003

Data Index: 125698 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1012. Min Act: -0.0003

Data Index: 949337 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0954. Min Act: -0.0003

Data Index: 1620448 (Python Code)

Max Activating Token Index: 128

Text #12

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0938. Min Act: -0.0003

Data Index: 1385715 (Python Code)

Max Activating Token Index: 222

Text #13

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0976. Min Act: -0.0003

Data Index: 48228 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0892. Min Act: -0.0003

Data Index: 1084671 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0881. Min Act: -0.0003

Data Index: 1214255 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0855. Min Act: -0.0003

Data Index: 366863 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0904. Min Act: -0.0003

Data Index: 644198 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0872. Min Act: -0.0003

Data Index: 827167 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0832. Min Act: -0.0003

Data Index: 1065510 (C4 (Web Text))

Max Activating Token Index: 174