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

Dataset: The Pile

Neuron 1921 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.8106. Min Act: -0.0000

Data Index: 976951 (The Pile)

Max Activating Token Index: 526

Text #1

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.8106. Min Act: -0.0000

Data Index: 1557720 (The Pile)

Max Activating Token Index: 964

Text #2

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5913. Min Act: -0.0000

Data Index: 269846 (The Pile)

Max Activating Token Index: 638

Text #3

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5229. Min Act: -0.0000

Data Index: 1676195 (The Pile)

Max Activating Token Index: 251

Text #4

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5123. Min Act: -0.0000

Data Index: 16090 (The Pile)

Max Activating Token Index: 864

Text #5

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5298. Min Act: -0.0000

Data Index: 49294 (The Pile)

Max Activating Token Index: 55

Text #6

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4862. Min Act: -0.0000

Data Index: 781671 (The Pile)

Max Activating Token Index: 778

Text #7

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5009. Min Act: -0.0000

Data Index: 1890997 (The Pile)

Max Activating Token Index: 855

Text #8

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4342. Min Act: -0.0000

Data Index: 841537 (The Pile)

Max Activating Token Index: 590

Text #9

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4093. Min Act: -0.0000

Data Index: 1625555 (The Pile)

Max Activating Token Index: 584

Text #10

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4474. Min Act: -0.0000

Data Index: 1959933 (The Pile)

Max Activating Token Index: 781

Text #11

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4338. Min Act: -0.0000

Data Index: 443282 (The Pile)

Max Activating Token Index: 20

Text #12

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4415. Min Act: -0.0000

Data Index: 715802 (The Pile)

Max Activating Token Index: 1015

Text #13

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1607540 (The Pile)

Max Activating Token Index: 447

Text #14

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4396. Min Act: -0.0000

Data Index: 395056 (The Pile)

Max Activating Token Index: 892

Text #15

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1691131 (The Pile)

Max Activating Token Index: 745

Text #16

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4184. Min Act: -0.0000

Data Index: 220452 (The Pile)

Max Activating Token Index: 616

Text #17

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4261. Min Act: -0.0000

Data Index: 59931 (The Pile)

Max Activating Token Index: 353

Text #18

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1702779 (The Pile)

Max Activating Token Index: 846

Text #19

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.3663. Min Act: -0.0000

Data Index: 629941 (The Pile)

Max Activating Token Index: 523