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

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

Neuron 1389 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: 0.3270. Min Range: -0.3270

Max Act: 0.3270. Min Act: 0.0000

Data Index: 1368124 (Python Code)

Max Activating Token Index: 790

Text #1

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1523454 (Python Code)

Max Activating Token Index: 395

Text #2

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.3039. Min Act: 0.0000

Data Index: 1442648 (Python Code)

Max Activating Token Index: 982

Text #3

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1590835 (Python Code)

Max Activating Token Index: 180

Text #4

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1627787 (Python Code)

Max Activating Token Index: 471

Text #5

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1580694 (Python Code)

Max Activating Token Index: 906

Text #6

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2424. Min Act: -0.0000

Data Index: 1559133 (Python Code)

Max Activating Token Index: 974

Text #7

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2326. Min Act: 0.0000

Data Index: 1538601 (Python Code)

Max Activating Token Index: 103

Text #8

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1576228 (Python Code)

Max Activating Token Index: 105

Text #9

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2208. Min Act: 0.0000

Data Index: 1620347 (Python Code)

Max Activating Token Index: 636

Text #10

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1394050 (Python Code)

Max Activating Token Index: 45

Text #11

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2278. Min Act: -0.0000

Data Index: 320555 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1450041 (Python Code)

Max Activating Token Index: 812

Text #13

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2175. Min Act: -0.0000

Data Index: 1373761 (Python Code)

Max Activating Token Index: 393

Text #14

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2295. Min Act: -0.0000

Data Index: 1423816 (Python Code)

Max Activating Token Index: 93

Text #15

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2115. Min Act: -0.0000

Data Index: 1615353 (Python Code)

Max Activating Token Index: 836

Text #16

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2217. Min Act: -0.0000

Data Index: 1440101 (Python Code)

Max Activating Token Index: 350

Text #17

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2075. Min Act: -0.0000

Data Index: 67138 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2113. Min Act: -0.0000

Data Index: 1523882 (Python Code)

Max Activating Token Index: 993

Text #19

Max Range: 0.3270. Min Range: -0.3270

Max Act: 0.2040. Min Act: -0.0000

Data Index: 1653291 (Python Code)

Max Activating Token Index: 467