Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2242 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.8148. Min Range: -3.8148

Max Act: 3.7940. Min Act: -0.0001

Data Index: 1433853 (Python Code)

Max Activating Token Index: 646

Text #1

Max Range: 3.8148. Min Range: -3.8148

Max Act: 3.8148. Min Act: -0.0001

Data Index: 1625651 (Python Code)

Max Activating Token Index: 563

Text #2

Max Range: 3.8148. Min Range: -3.8148

Max Act: 3.5171. Min Act: -0.0001

Data Index: 1517117 (Python Code)

Max Activating Token Index: 719

Text #3

Max Range: 3.8148. Min Range: -3.8148

Max Act: 3.3777. Min Act: -0.0001

Data Index: 1410863 (Python Code)

Max Activating Token Index: 370

Text #4

Max Range: 3.8148. Min Range: -3.8148

Max Act: 3.5100. Min Act: -0.0001

Data Index: 1555158 (Python Code)

Max Activating Token Index: 360

Text #5

Max Range: 3.8148. Min Range: -3.8148

Max Act: 3.3155. Min Act: -0.0001

Data Index: 1382728 (Python Code)

Max Activating Token Index: 710

Text #6

Max Range: 3.8148. Min Range: -3.8148

Max Act: 3.2766. Min Act: -0.0001

Data Index: 1373503 (Python Code)

Max Activating Token Index: 246

Text #7

Max Range: 3.8148. Min Range: -3.8148

Max Act: 3.5669. Min Act: -0.0001

Data Index: 1422016 (Python Code)

Max Activating Token Index: 462

Text #8

Max Range: 3.8148. Min Range: -3.8148

Max Act: 3.5283. Min Act: -0.0001

Data Index: 1546280 (Python Code)

Max Activating Token Index: 504

Text #9

Max Range: 3.8148. Min Range: -3.8148

Max Act: 3.0995. Min Act: -0.0001

Data Index: 1565774 (Python Code)

Max Activating Token Index: 723

Text #10

Max Range: 3.8148. Min Range: -3.8148

Max Act: 3.2119. Min Act: -0.0001

Data Index: 1410943 (Python Code)

Max Activating Token Index: 160

Text #11

Max Range: 3.8148. Min Range: -3.8148

Max Act: 3.3318. Min Act: -0.0001

Data Index: 1621361 (Python Code)

Max Activating Token Index: 518

Text #12

Max Range: 3.8148. Min Range: -3.8148

Max Act: 3.7890. Min Act: -0.0001

Data Index: 1568801 (Python Code)

Max Activating Token Index: 716

Text #13

Max Range: 3.8148. Min Range: -3.8148

Max Act: 3.4674. Min Act: -0.0001

Data Index: 1649938 (Python Code)

Max Activating Token Index: 1018

Text #14

Max Range: 3.8148. Min Range: -3.8148

Max Act: 3.1415. Min Act: -0.0001

Data Index: 1430961 (Python Code)

Max Activating Token Index: 766

Text #15

Max Range: 3.8148. Min Range: -3.8148

Max Act: 3.2717. Min Act: -0.0001

Data Index: 1628432 (Python Code)

Max Activating Token Index: 323

Text #16

Max Range: 3.8148. Min Range: -3.8148

Max Act: 3.2141. Min Act: -0.0001

Data Index: 1396561 (Python Code)

Max Activating Token Index: 774

Text #17

Max Range: 3.8148. Min Range: -3.8148

Max Act: 3.0689. Min Act: -0.0001

Data Index: 1604864 (Python Code)

Max Activating Token Index: 836

Text #18

Max Range: 3.8148. Min Range: -3.8148

Max Act: 3.0445. Min Act: -0.0001

Data Index: 1641933 (Python Code)

Max Activating Token Index: 885

Text #19

Max Range: 3.8148. Min Range: -3.8148

Max Act: 3.0455. Min Act: -0.0001

Data Index: 1536884 (Python Code)

Max Activating Token Index: 392