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

Dataset: The Pile

Neuron 4115 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: 3.3092. Min Range: -3.3092

Max Act: 3.3092. Min Act: -0.0000

Data Index: 968011 (The Pile)

Max Activating Token Index: 235

Text #1

Max Range: 3.3092. Min Range: -3.3092

Max Act: 3.1919. Min Act: -0.0000

Data Index: 1284949 (The Pile)

Max Activating Token Index: 265

Text #2

Max Range: 3.3092. Min Range: -3.3092

Max Act: 2.5580. Min Act: -0.0000

Data Index: 820640 (The Pile)

Max Activating Token Index: 727

Text #3

Max Range: 3.3092. Min Range: -3.3092

Max Act: 2.5237. Min Act: -0.0000

Data Index: 645841 (The Pile)

Max Activating Token Index: 844

Text #4

Max Range: 3.3092. Min Range: -3.3092

Max Act: 2.6206. Min Act: -0.0000

Data Index: 872688 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 3.3092. Min Range: -3.3092

Max Act: 2.5966. Min Act: -0.0000

Data Index: 971822 (The Pile)

Max Activating Token Index: 687

Text #6

Max Range: 3.3092. Min Range: -3.3092

Max Act: 3.0186. Min Act: -0.0000

Data Index: 1897560 (The Pile)

Max Activating Token Index: 987

Text #7

Max Range: 3.3092. Min Range: -3.3092

Max Act: 2.5774. Min Act: -0.0000

Data Index: 1451190 (The Pile)

Max Activating Token Index: 116

Text #8

Max Range: 3.3092. Min Range: -3.3092

Max Act: 2.6961. Min Act: -0.0000

Data Index: 1245596 (The Pile)

Max Activating Token Index: 112

Text #9

Max Range: 3.3092. Min Range: -3.3092

Max Act: 2.5367. Min Act: -0.0000

Data Index: 1598016 (The Pile)

Max Activating Token Index: 795

Text #10

Max Range: 3.3092. Min Range: -3.3092

Max Act: 2.0588. Min Act: -0.0000

Data Index: 911139 (The Pile)

Max Activating Token Index: 212

Text #11

Max Range: 3.3092. Min Range: -3.3092

Max Act: 2.4079. Min Act: -0.0000

Data Index: 753820 (The Pile)

Max Activating Token Index: 117

Text #12

Max Range: 3.3092. Min Range: -3.3092

Max Act: 2.1265. Min Act: -0.0000

Data Index: 1100031 (The Pile)

Max Activating Token Index: 526

Text #13

Max Range: 3.3092. Min Range: -3.3092

Max Act: 2.3949. Min Act: -0.0000

Data Index: 269498 (The Pile)

Max Activating Token Index: 716

Text #14

Max Range: 3.3092. Min Range: -3.3092

Max Act: 2.1797. Min Act: -0.0000

Data Index: 1342912 (The Pile)

Max Activating Token Index: 925

Text #15

Max Range: 3.3092. Min Range: -3.3092

Max Act: 2.2294. Min Act: -0.0000

Data Index: 741094 (The Pile)

Max Activating Token Index: 419

Text #16

Max Range: 3.3092. Min Range: -3.3092

Max Act: 2.3949. Min Act: -0.0000

Data Index: 1206554 (The Pile)

Max Activating Token Index: 648

Text #17

Max Range: 3.3092. Min Range: -3.3092

Max Act: 2.5010. Min Act: -0.0000

Data Index: 1706882 (The Pile)

Max Activating Token Index: 862

Text #18

Max Range: 3.3092. Min Range: -3.3092

Max Act: 2.1457. Min Act: -0.0000

Data Index: 246930 (The Pile)

Max Activating Token Index: 545

Text #19

Max Range: 3.3092. Min Range: -3.3092

Max Act: 2.1347. Min Act: -0.0000

Data Index: 1930064 (The Pile)

Max Activating Token Index: 163