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

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

Neuron 1797 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: 0.9312. Min Range: -0.9312

Max Act: 0.9312. Min Act: -0.0001

Data Index: 1492404 (Python Code)

Max Activating Token Index: 723

Text #1

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.9109. Min Act: -0.0001

Data Index: 1387243 (Python Code)

Max Activating Token Index: 193

Text #2

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.8349. Min Act: -0.0001

Data Index: 1626146 (Python Code)

Max Activating Token Index: 713

Text #3

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.8275. Min Act: -0.0001

Data Index: 1380377 (Python Code)

Max Activating Token Index: 823

Text #4

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.8058. Min Act: -0.0001

Data Index: 1456557 (Python Code)

Max Activating Token Index: 987

Text #5

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.8233. Min Act: -0.0001

Data Index: 1529966 (Python Code)

Max Activating Token Index: 568

Text #6

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.8062. Min Act: -0.0001

Data Index: 1529147 (Python Code)

Max Activating Token Index: 865

Text #7

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7749. Min Act: -0.0001

Data Index: 1396212 (Python Code)

Max Activating Token Index: 699

Text #8

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7557. Min Act: -0.0001

Data Index: 1584173 (Python Code)

Max Activating Token Index: 195

Text #9

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7687. Min Act: -0.0001

Data Index: 1433292 (Python Code)

Max Activating Token Index: 715

Text #10

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7927. Min Act: -0.0001

Data Index: 1361715 (Python Code)

Max Activating Token Index: 996

Text #11

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7625. Min Act: -0.0001

Data Index: 1603467 (Python Code)

Max Activating Token Index: 853

Text #12

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7539. Min Act: -0.0000

Data Index: 1396251 (Python Code)

Max Activating Token Index: 233

Text #13

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7530. Min Act: -0.0001

Data Index: 1497514 (Python Code)

Max Activating Token Index: 475

Text #14

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7777. Min Act: -0.0001

Data Index: 1590598 (Python Code)

Max Activating Token Index: 666

Text #15

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7469. Min Act: -0.0001

Data Index: 1372462 (Python Code)

Max Activating Token Index: 338

Text #16

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.6968. Min Act: -0.0001

Data Index: 1548468 (Python Code)

Max Activating Token Index: 661

Text #17

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7363. Min Act: -0.0001

Data Index: 1363281 (Python Code)

Max Activating Token Index: 140

Text #18

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7481. Min Act: -0.0001

Data Index: 1655887 (Python Code)

Max Activating Token Index: 1014

Text #19

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7292. Min Act: -0.0001

Data Index: 1655224 (Python Code)

Max Activating Token Index: 536