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

Dataset: The Pile

Neuron 4813 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: 0.6702. Min Range: -0.6702

Max Act: 0.5397. Min Act: -0.0000

Data Index: 46326 (The Pile)

Max Activating Token Index: 286

Text #1

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1306063 (The Pile)

Max Activating Token Index: 144

Text #2

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.6702. Min Act: -0.0000

Data Index: 683635 (The Pile)

Max Activating Token Index: 606

Text #3

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5482. Min Act: -0.0000

Data Index: 1424920 (The Pile)

Max Activating Token Index: 682

Text #4

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1207755 (The Pile)

Max Activating Token Index: 862

Text #5

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1000705 (The Pile)

Max Activating Token Index: 801

Text #6

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5135. Min Act: -0.0000

Data Index: 1881983 (The Pile)

Max Activating Token Index: 927

Text #7

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5223. Min Act: -0.0000

Data Index: 872779 (The Pile)

Max Activating Token Index: 284

Text #8

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.6046. Min Act: -0.0000

Data Index: 755042 (The Pile)

Max Activating Token Index: 876

Text #9

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5098. Min Act: -0.0000

Data Index: 502833 (The Pile)

Max Activating Token Index: 990

Text #10

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4175. Min Act: -0.0000

Data Index: 1213403 (The Pile)

Max Activating Token Index: 562

Text #11

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4815. Min Act: -0.0000

Data Index: 461267 (The Pile)

Max Activating Token Index: 303

Text #12

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4743. Min Act: -0.0000

Data Index: 136267 (The Pile)

Max Activating Token Index: 438

Text #13

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4321. Min Act: -0.0000

Data Index: 1868678 (The Pile)

Max Activating Token Index: 296

Text #14

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4177. Min Act: -0.0000

Data Index: 567640 (The Pile)

Max Activating Token Index: 286

Text #15

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4876. Min Act: -0.0000

Data Index: 756980 (The Pile)

Max Activating Token Index: 572

Text #16

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5177. Min Act: -0.0000

Data Index: 205148 (The Pile)

Max Activating Token Index: 913

Text #17

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4708. Min Act: -0.0000

Data Index: 1544753 (The Pile)

Max Activating Token Index: 833

Text #18

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4396. Min Act: -0.0000

Data Index: 1372525 (The Pile)

Max Activating Token Index: 301

Text #19

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4566. Min Act: -0.0000

Data Index: 337096 (The Pile)

Max Activating Token Index: 543