Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 406 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.2104. Min Act: -0.0000

Data Index: 399925 (The Pile)

Max Activating Token Index: 306

Text #1

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1775. Min Act: -0.0000

Data Index: 1827971 (The Pile)

Max Activating Token Index: 617

Text #2

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1066917 (The Pile)

Max Activating Token Index: 677

Text #3

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1779. Min Act: -0.0000

Data Index: 1766694 (The Pile)

Max Activating Token Index: 927

Text #4

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1550. Min Act: -0.0000

Data Index: 304006 (The Pile)

Max Activating Token Index: 82

Text #5

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1611. Min Act: -0.0000

Data Index: 1356195 (The Pile)

Max Activating Token Index: 223

Text #6

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1585. Min Act: -0.0000

Data Index: 342751 (The Pile)

Max Activating Token Index: 633

Text #7

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1128533 (The Pile)

Max Activating Token Index: 425

Text #8

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1096500 (The Pile)

Max Activating Token Index: 238

Text #9

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1462. Min Act: -0.0000

Data Index: 793267 (The Pile)

Max Activating Token Index: 228

Text #10

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1279. Min Act: -0.0000

Data Index: 287807 (The Pile)

Max Activating Token Index: 957

Text #11

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1453. Min Act: -0.0000

Data Index: 119704 (The Pile)

Max Activating Token Index: 570

Text #12

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1180. Min Act: -0.0000

Data Index: 917431 (The Pile)

Max Activating Token Index: 837

Text #13

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1250. Min Act: -0.0000

Data Index: 90036 (The Pile)

Max Activating Token Index: 990

Text #14

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1395. Min Act: -0.0000

Data Index: 323930 (The Pile)

Max Activating Token Index: 172

Text #15

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1917536 (The Pile)

Max Activating Token Index: 466

Text #16

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1306. Min Act: -0.0000

Data Index: 589906 (The Pile)

Max Activating Token Index: 340

Text #17

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1420. Min Act: -0.0000

Data Index: 412881 (The Pile)

Max Activating Token Index: 60

Text #18

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1375. Min Act: -0.0000

Data Index: 1569465 (The Pile)

Max Activating Token Index: 258

Text #19

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1344. Min Act: -0.0000

Data Index: 1495539 (The Pile)

Max Activating Token Index: 529