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

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

Neuron 206 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: 0.1840. Min Range: -0.1840

Max Act: 0.1840. Min Act: -0.0001

Data Index: 235495 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1780. Min Act: -0.0001

Data Index: 649624 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1548. Min Act: -0.0001

Data Index: 758898 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1612. Min Act: -0.0001

Data Index: 1011387 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1562. Min Act: -0.0001

Data Index: 720335 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1403. Min Act: -0.0001

Data Index: 1040932 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1398. Min Act: -0.0001

Data Index: 537400 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1260. Min Act: -0.0001

Data Index: 148056 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1287. Min Act: -0.0001

Data Index: 1040827 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1290. Min Act: -0.0001

Data Index: 1356118 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1345. Min Act: -0.0001

Data Index: 480879 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1146. Min Act: -0.0001

Data Index: 726124 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1262. Min Act: -0.0001

Data Index: 631030 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1254. Min Act: -0.0001

Data Index: 708359 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1236. Min Act: -0.0001

Data Index: 618470 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1232. Min Act: -0.0001

Data Index: 589849 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1177. Min Act: -0.0001

Data Index: 481103 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1212. Min Act: -0.0001

Data Index: 1152866 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1211. Min Act: -0.0001

Data Index: 47053 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1237. Min Act: -0.0001

Data Index: 383539 (C4 (Web Text))

Max Activating Token Index: 195