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

Dataset: The Pile

Neuron 3372 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: 4.9114. Min Range: -4.9114

Max Act: 4.4462. Min Act: -0.0000

Data Index: 1703201 (The Pile)

Max Activating Token Index: 870

Text #1

Max Range: 4.9114. Min Range: -4.9114

Max Act: 4.8619. Min Act: -0.0000

Data Index: 256390 (The Pile)

Max Activating Token Index: 672

Text #2

Max Range: 4.9114. Min Range: -4.9114

Max Act: 4.9114. Min Act: -0.0000

Data Index: 1555680 (The Pile)

Max Activating Token Index: 966

Text #3

Max Range: 4.9114. Min Range: -4.9114

Max Act: 4.4594. Min Act: -0.0000

Data Index: 671464 (The Pile)

Max Activating Token Index: 10

Text #4

Max Range: 4.9114. Min Range: -4.9114

Max Act: 4.4963. Min Act: -0.0000

Data Index: 1008802 (The Pile)

Max Activating Token Index: 308

Text #5

Max Range: 4.9114. Min Range: -4.9114

Max Act: 4.5366. Min Act: -0.0000

Data Index: 1815661 (The Pile)

Max Activating Token Index: 450

Text #6

Max Range: 4.9114. Min Range: -4.9114

Max Act: 4.3438. Min Act: -0.0000

Data Index: 506438 (The Pile)

Max Activating Token Index: 8

Text #7

Max Range: 4.9114. Min Range: -4.9114

Max Act: 4.1482. Min Act: -0.0000

Data Index: 1088321 (The Pile)

Max Activating Token Index: 555

Text #8

Max Range: 4.9114. Min Range: -4.9114

Max Act: 3.8870. Min Act: -0.0000

Data Index: 1183795 (The Pile)

Max Activating Token Index: 441

Text #9

Max Range: 4.9114. Min Range: -4.9114

Max Act: 4.4266. Min Act: -0.0000

Data Index: 1234899 (The Pile)

Max Activating Token Index: 889

Text #10

Max Range: 4.9114. Min Range: -4.9114

Max Act: 4.3843. Min Act: -0.0000

Data Index: 439984 (The Pile)

Max Activating Token Index: 8

Text #11

Max Range: 4.9114. Min Range: -4.9114

Max Act: 4.3083. Min Act: -0.0000

Data Index: 1394117 (The Pile)

Max Activating Token Index: 253

Text #12

Max Range: 4.9114. Min Range: -4.9114

Max Act: 4.3199. Min Act: -0.0000

Data Index: 1108507 (The Pile)

Max Activating Token Index: 10

Text #13

Max Range: 4.9114. Min Range: -4.9114

Max Act: 4.1298. Min Act: -0.0000

Data Index: 1409017 (The Pile)

Max Activating Token Index: 819

Text #14

Max Range: 4.9114. Min Range: -4.9114

Max Act: 3.9560. Min Act: -0.0000

Data Index: 1613164 (The Pile)

Max Activating Token Index: 10

Text #15

Max Range: 4.9114. Min Range: -4.9114

Max Act: 4.2610. Min Act: -0.0000

Data Index: 1011513 (The Pile)

Max Activating Token Index: 119

Text #16

Max Range: 4.9114. Min Range: -4.9114

Max Act: 4.2431. Min Act: -0.0000

Data Index: 1126692 (The Pile)

Max Activating Token Index: 8

Text #17

Max Range: 4.9114. Min Range: -4.9114

Max Act: 4.3404. Min Act: -0.0000

Data Index: 680485 (The Pile)

Max Activating Token Index: 645

Text #18

Max Range: 4.9114. Min Range: -4.9114

Max Act: 4.1937. Min Act: -0.0000

Data Index: 1297610 (The Pile)

Max Activating Token Index: 165

Text #19

Max Range: 4.9114. Min Range: -4.9114

Max Act: 4.0787. Min Act: -0.0000

Data Index: 971184 (The Pile)

Max Activating Token Index: 10