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

Dataset: The Pile

Neuron 3739 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1771002 (The Pile)

Max Activating Token Index: 50

Text #1

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1595. Min Act: -0.0000

Data Index: 455340 (The Pile)

Max Activating Token Index: 857

Text #2

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1595. Min Act: -0.0000

Data Index: 964043 (The Pile)

Max Activating Token Index: 544

Text #3

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1456. Min Act: -0.0000

Data Index: 1395809 (The Pile)

Max Activating Token Index: 791

Text #4

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1439. Min Act: -0.0000

Data Index: 1778562 (The Pile)

Max Activating Token Index: 916

Text #5

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1262. Min Act: -0.0000

Data Index: 123072 (The Pile)

Max Activating Token Index: 610

Text #6

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1402. Min Act: -0.0000

Data Index: 980221 (The Pile)

Max Activating Token Index: 702

Text #7

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1369. Min Act: -0.0000

Data Index: 64739 (The Pile)

Max Activating Token Index: 497

Text #8

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1456. Min Act: -0.0000

Data Index: 1225049 (The Pile)

Max Activating Token Index: 908

Text #9

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1339. Min Act: -0.0000

Data Index: 1420394 (The Pile)

Max Activating Token Index: 194

Text #10

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1246. Min Act: -0.0000

Data Index: 1770506 (The Pile)

Max Activating Token Index: 948

Text #11

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1381. Min Act: -0.0000

Data Index: 1158469 (The Pile)

Max Activating Token Index: 184

Text #12

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1979741 (The Pile)

Max Activating Token Index: 729

Text #13

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1389. Min Act: -0.0000

Data Index: 87259 (The Pile)

Max Activating Token Index: 114

Text #14

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1250. Min Act: -0.0000

Data Index: 770241 (The Pile)

Max Activating Token Index: 331

Text #15

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1278. Min Act: -0.0000

Data Index: 217303 (The Pile)

Max Activating Token Index: 396

Text #16

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1324. Min Act: -0.0000

Data Index: 513148 (The Pile)

Max Activating Token Index: 716

Text #17

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1301. Min Act: -0.0000

Data Index: 1806509 (The Pile)

Max Activating Token Index: 861

Text #18

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1306. Min Act: -0.0000

Data Index: 492134 (The Pile)

Max Activating Token Index: 209

Text #19

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1230. Min Act: -0.0000

Data Index: 472165 (The Pile)

Max Activating Token Index: 216