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

Dataset: The Pile

Neuron 1163 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: 1.7880. Min Range: -1.7880

Max Act: 1.7880. Min Act: -0.0000

Data Index: 970293 (The Pile)

Max Activating Token Index: 253

Text #1

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.6557. Min Act: -0.0000

Data Index: 1951746 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.6058. Min Act: -0.0000

Data Index: 1429436 (The Pile)

Max Activating Token Index: 528

Text #3

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.5883. Min Act: -0.0000

Data Index: 1900521 (The Pile)

Max Activating Token Index: 935

Text #4

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.5618. Min Act: -0.0000

Data Index: 1638604 (The Pile)

Max Activating Token Index: 285

Text #5

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.5691. Min Act: -0.0000

Data Index: 35276 (The Pile)

Max Activating Token Index: 1008

Text #6

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.4290. Min Act: -0.0000

Data Index: 1142218 (The Pile)

Max Activating Token Index: 914

Text #7

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.5079. Min Act: -0.0000

Data Index: 504649 (The Pile)

Max Activating Token Index: 931

Text #8

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.4321. Min Act: -0.0000

Data Index: 454292 (The Pile)

Max Activating Token Index: 902

Text #9

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.5866. Min Act: -0.0000

Data Index: 1653250 (The Pile)

Max Activating Token Index: 804

Text #10

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.4971. Min Act: -0.0000

Data Index: 1106267 (The Pile)

Max Activating Token Index: 282

Text #11

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.3956. Min Act: -0.0000

Data Index: 504251 (The Pile)

Max Activating Token Index: 461

Text #12

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.4503. Min Act: -0.0000

Data Index: 1949812 (The Pile)

Max Activating Token Index: 455

Text #13

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.3603. Min Act: -0.0000

Data Index: 1630704 (The Pile)

Max Activating Token Index: 900

Text #14

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.4170. Min Act: -0.0000

Data Index: 1309884 (The Pile)

Max Activating Token Index: 248

Text #15

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.5026. Min Act: -0.0000

Data Index: 377006 (The Pile)

Max Activating Token Index: 404

Text #16

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.4177. Min Act: -0.0000

Data Index: 535778 (The Pile)

Max Activating Token Index: 517

Text #17

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.4960. Min Act: -0.0000

Data Index: 1247175 (The Pile)

Max Activating Token Index: 1007

Text #18

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.4808. Min Act: -0.0000

Data Index: 1471520 (The Pile)

Max Activating Token Index: 190

Text #19

Max Range: 1.7880. Min Range: -1.7880

Max Act: 1.3104. Min Act: -0.0000

Data Index: 795031 (The Pile)

Max Activating Token Index: 637