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

Dataset: The Pile

Neuron 1359 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: 0.5728. Min Range: -0.5728

Max Act: 0.5524. Min Act: -0.0000

Data Index: 296489 (The Pile)

Max Activating Token Index: 465

Text #1

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.5728. Min Act: -0.0000

Data Index: 832398 (The Pile)

Max Activating Token Index: 916

Text #2

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1353031 (The Pile)

Max Activating Token Index: 808

Text #3

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4403. Min Act: -0.0000

Data Index: 733531 (The Pile)

Max Activating Token Index: 630

Text #4

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4612. Min Act: -0.0000

Data Index: 1754226 (The Pile)

Max Activating Token Index: 723

Text #5

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4359. Min Act: -0.0000

Data Index: 1418088 (The Pile)

Max Activating Token Index: 801

Text #6

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4026. Min Act: -0.0000

Data Index: 1443129 (The Pile)

Max Activating Token Index: 781

Text #7

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4224. Min Act: -0.0000

Data Index: 1419941 (The Pile)

Max Activating Token Index: 457

Text #8

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4051. Min Act: -0.0000

Data Index: 825318 (The Pile)

Max Activating Token Index: 570

Text #9

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4049. Min Act: -0.0000

Data Index: 239136 (The Pile)

Max Activating Token Index: 198

Text #10

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4268. Min Act: -0.0000

Data Index: 87462 (The Pile)

Max Activating Token Index: 810

Text #11

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4073. Min Act: -0.0000

Data Index: 1729139 (The Pile)

Max Activating Token Index: 964

Text #12

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.3863. Min Act: -0.0000

Data Index: 558210 (The Pile)

Max Activating Token Index: 133

Text #13

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.3576. Min Act: -0.0000

Data Index: 224313 (The Pile)

Max Activating Token Index: 948

Text #14

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1042431 (The Pile)

Max Activating Token Index: 140

Text #15

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1218010 (The Pile)

Max Activating Token Index: 170

Text #16

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.3809. Min Act: -0.0000

Data Index: 5809 (The Pile)

Max Activating Token Index: 375

Text #17

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.3896. Min Act: -0.0000

Data Index: 1910677 (The Pile)

Max Activating Token Index: 626

Text #18

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1220716 (The Pile)

Max Activating Token Index: 797

Text #19

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.3781. Min Act: -0.0000

Data Index: 63695 (The Pile)

Max Activating Token Index: 141