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

Dataset: The Pile

Neuron 37 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3637. Min Range: -1.3637

Max Act: 1.3637. Min Act: -0.0000

Data Index: 130528 (The Pile)

Max Activating Token Index: 781

Text #1

Max Range: 1.3637. Min Range: -1.3637

Max Act: 1.3059. Min Act: -0.0000

Data Index: 1856947 (The Pile)

Max Activating Token Index: 367

Text #2

Max Range: 1.3637. Min Range: -1.3637

Max Act: 1.1746. Min Act: -0.0000

Data Index: 1341226 (The Pile)

Max Activating Token Index: 989

Text #3

Max Range: 1.3637. Min Range: -1.3637

Max Act: 1.1689. Min Act: -0.0000

Data Index: 25872 (The Pile)

Max Activating Token Index: 420

Text #4

Max Range: 1.3637. Min Range: -1.3637

Max Act: 1.1009. Min Act: -0.0000

Data Index: 672417 (The Pile)

Max Activating Token Index: 335

Text #5

Max Range: 1.3637. Min Range: -1.3637

Max Act: 1.0260. Min Act: -0.0000

Data Index: 794297 (The Pile)

Max Activating Token Index: 82

Text #6

Max Range: 1.3637. Min Range: -1.3637

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1062738 (The Pile)

Max Activating Token Index: 336

Text #7

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.9374. Min Act: -0.0000

Data Index: 867909 (The Pile)

Max Activating Token Index: 500

Text #8

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.9554. Min Act: -0.0000

Data Index: 174528 (The Pile)

Max Activating Token Index: 1001

Text #9

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.9587. Min Act: -0.0000

Data Index: 254008 (The Pile)

Max Activating Token Index: 630

Text #10

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.9462. Min Act: -0.0000

Data Index: 86097 (The Pile)

Max Activating Token Index: 681

Text #11

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.9205. Min Act: -0.0000

Data Index: 483190 (The Pile)

Max Activating Token Index: 793

Text #12

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.9073. Min Act: -0.0000

Data Index: 164388 (The Pile)

Max Activating Token Index: 930

Text #13

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.9058. Min Act: -0.0000

Data Index: 1493109 (The Pile)

Max Activating Token Index: 589

Text #14

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.8701. Min Act: -0.0000

Data Index: 370672 (The Pile)

Max Activating Token Index: 602

Text #15

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.8915. Min Act: -0.0000

Data Index: 1346542 (The Pile)

Max Activating Token Index: 684

Text #16

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.9411. Min Act: -0.0000

Data Index: 1546957 (The Pile)

Max Activating Token Index: 432

Text #17

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.7858. Min Act: -0.0000

Data Index: 188849 (The Pile)

Max Activating Token Index: 852

Text #18

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1457146 (The Pile)

Max Activating Token Index: 42

Text #19

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.8418. Min Act: -0.0000

Data Index: 204253 (The Pile)

Max Activating Token Index: 279