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

Dataset: The Pile

Neuron 895 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 5.1868. Min Range: -5.1868

Max Act: 4.9787. Min Act: -0.0000

Data Index: 229363 (The Pile)

Max Activating Token Index: 552

Text #1

Max Range: 5.1868. Min Range: -5.1868

Max Act: 4.6735. Min Act: -0.0000

Data Index: 880774 (The Pile)

Max Activating Token Index: 773

Text #2

Max Range: 5.1868. Min Range: -5.1868

Max Act: 5.0025. Min Act: -0.0000

Data Index: 74063 (The Pile)

Max Activating Token Index: 118

Text #3

Max Range: 5.1868. Min Range: -5.1868

Max Act: 5.1868. Min Act: -0.0000

Data Index: 278705 (The Pile)

Max Activating Token Index: 135

Text #4

Max Range: 5.1868. Min Range: -5.1868

Max Act: 4.5381. Min Act: -0.0000

Data Index: 531673 (The Pile)

Max Activating Token Index: 996

Text #5

Max Range: 5.1868. Min Range: -5.1868

Max Act: 4.5487. Min Act: -0.0000

Data Index: 1957716 (The Pile)

Max Activating Token Index: 441

Text #6

Max Range: 5.1868. Min Range: -5.1868

Max Act: 4.4979. Min Act: -0.0000

Data Index: 472536 (The Pile)

Max Activating Token Index: 772

Text #7

Max Range: 5.1868. Min Range: -5.1868

Max Act: 4.2911. Min Act: -0.0000

Data Index: 400217 (The Pile)

Max Activating Token Index: 895

Text #8

Max Range: 5.1868. Min Range: -5.1868

Max Act: 4.5533. Min Act: -0.0000

Data Index: 46410 (The Pile)

Max Activating Token Index: 981

Text #9

Max Range: 5.1868. Min Range: -5.1868

Max Act: 4.1616. Min Act: -0.0000

Data Index: 907197 (The Pile)

Max Activating Token Index: 427

Text #10

Max Range: 5.1868. Min Range: -5.1868

Max Act: 3.6948. Min Act: -0.0000

Data Index: 1774054 (The Pile)

Max Activating Token Index: 879

Text #11

Max Range: 5.1868. Min Range: -5.1868

Max Act: 4.0145. Min Act: -0.0000

Data Index: 349117 (The Pile)

Max Activating Token Index: 526

Text #12

Max Range: 5.1868. Min Range: -5.1868

Max Act: 3.8781. Min Act: -0.0000

Data Index: 1255139 (The Pile)

Max Activating Token Index: 263

Text #13

Max Range: 5.1868. Min Range: -5.1868

Max Act: 3.7302. Min Act: -0.0000

Data Index: 562151 (The Pile)

Max Activating Token Index: 913

Text #14

Max Range: 5.1868. Min Range: -5.1868

Max Act: 4.1282. Min Act: -0.0000

Data Index: 958317 (The Pile)

Max Activating Token Index: 762

Text #15

Max Range: 5.1868. Min Range: -5.1868

Max Act: 3.9662. Min Act: -0.0000

Data Index: 927530 (The Pile)

Max Activating Token Index: 40

Text #16

Max Range: 5.1868. Min Range: -5.1868

Max Act: 3.5753. Min Act: -0.0000

Data Index: 152821 (The Pile)

Max Activating Token Index: 544

Text #17

Max Range: 5.1868. Min Range: -5.1868

Max Act: 3.5725. Min Act: -0.0000

Data Index: 356238 (The Pile)

Max Activating Token Index: 270

Text #18

Max Range: 5.1868. Min Range: -5.1868

Max Act: 3.6858. Min Act: -0.0000

Data Index: 1834933 (The Pile)

Max Activating Token Index: 237

Text #19

Max Range: 5.1868. Min Range: -5.1868

Max Act: 3.7830. Min Act: -0.0000

Data Index: 557938 (The Pile)

Max Activating Token Index: 38