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

Dataset: The Pile

Neuron 1523 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: 0.1904. Min Range: -0.1904

Max Act: 0.1682. Min Act: -0.0000

Data Index: 736599 (The Pile)

Max Activating Token Index: 669

Text #1

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1904. Min Act: -0.0000

Data Index: 680990 (The Pile)

Max Activating Token Index: 787

Text #2

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1580. Min Act: -0.0000

Data Index: 1680954 (The Pile)

Max Activating Token Index: 477

Text #3

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1562. Min Act: -0.0000

Data Index: 1160317 (The Pile)

Max Activating Token Index: 603

Text #4

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1543060 (The Pile)

Max Activating Token Index: 829

Text #5

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1484. Min Act: -0.0000

Data Index: 703925 (The Pile)

Max Activating Token Index: 477

Text #6

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1471. Min Act: -0.0000

Data Index: 915687 (The Pile)

Max Activating Token Index: 951

Text #7

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1496. Min Act: -0.0000

Data Index: 215714 (The Pile)

Max Activating Token Index: 244

Text #8

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1527. Min Act: -0.0000

Data Index: 937403 (The Pile)

Max Activating Token Index: 857

Text #9

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1522. Min Act: -0.0000

Data Index: 1558024 (The Pile)

Max Activating Token Index: 998

Text #10

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1492. Min Act: -0.0000

Data Index: 1639523 (The Pile)

Max Activating Token Index: 220

Text #11

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1415. Min Act: -0.0000

Data Index: 922542 (The Pile)

Max Activating Token Index: 370

Text #12

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1894346 (The Pile)

Max Activating Token Index: 594

Text #13

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1870042 (The Pile)

Max Activating Token Index: 88

Text #14

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1309. Min Act: -0.0000

Data Index: 1360009 (The Pile)

Max Activating Token Index: 330

Text #15

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1304. Min Act: -0.0000

Data Index: 1344637 (The Pile)

Max Activating Token Index: 165

Text #16

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1371408 (The Pile)

Max Activating Token Index: 156

Text #17

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1481. Min Act: -0.0000

Data Index: 221477 (The Pile)

Max Activating Token Index: 159

Text #18

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1379. Min Act: -0.0000

Data Index: 464758 (The Pile)

Max Activating Token Index: 432

Text #19

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1414. Min Act: -0.0000

Data Index: 788142 (The Pile)

Max Activating Token Index: 748