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

Dataset: The Pile

Neuron 3504 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.2181. Min Act: -0.0001

Data Index: 1126480 (The Pile)

Max Activating Token Index: 21

Text #1

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1996. Min Act: -0.0001

Data Index: 809385 (The Pile)

Max Activating Token Index: 410

Text #2

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1757. Min Act: -0.0001

Data Index: 1444921 (The Pile)

Max Activating Token Index: 326

Text #3

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1713. Min Act: -0.0000

Data Index: 760282 (The Pile)

Max Activating Token Index: 15

Text #4

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1740. Min Act: -0.0001

Data Index: 208735 (The Pile)

Max Activating Token Index: 23

Text #5

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1598. Min Act: -0.0001

Data Index: 332772 (The Pile)

Max Activating Token Index: 130

Text #6

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1569. Min Act: -0.0001

Data Index: 1922150 (The Pile)

Max Activating Token Index: 457

Text #7

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1591. Min Act: -0.0001

Data Index: 799673 (The Pile)

Max Activating Token Index: 100

Text #8

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1414. Min Act: -0.0001

Data Index: 1778734 (The Pile)

Max Activating Token Index: 394

Text #9

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1354. Min Act: -0.0001

Data Index: 1104611 (The Pile)

Max Activating Token Index: 859

Text #10

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1385. Min Act: -0.0001

Data Index: 812194 (The Pile)

Max Activating Token Index: 783

Text #11

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1137793 (The Pile)

Max Activating Token Index: 816

Text #12

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1285. Min Act: -0.0001

Data Index: 501102 (The Pile)

Max Activating Token Index: 411

Text #13

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1366. Min Act: -0.0001

Data Index: 1680088 (The Pile)

Max Activating Token Index: 529

Text #14

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1330. Min Act: -0.0001

Data Index: 1707056 (The Pile)

Max Activating Token Index: 46

Text #15

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1259. Min Act: -0.0001

Data Index: 673674 (The Pile)

Max Activating Token Index: 610

Text #16

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1239. Min Act: -0.0001

Data Index: 140465 (The Pile)

Max Activating Token Index: 127

Text #17

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1364. Min Act: -0.0001

Data Index: 1636174 (The Pile)

Max Activating Token Index: 561

Text #18

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1310. Min Act: -0.0000

Data Index: 1795879 (The Pile)

Max Activating Token Index: 999

Text #19

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1256. Min Act: -0.0001

Data Index: 788014 (The Pile)

Max Activating Token Index: 313