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

Dataset: The Pile

Neuron 3115 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8343. Min Range: -0.8343

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1490741 (The Pile)

Max Activating Token Index: 928

Text #1

Max Range: 0.8343. Min Range: -0.8343

Max Act: 0.8343. Min Act: -0.0000

Data Index: 1758382 (The Pile)

Max Activating Token Index: 303

Text #2

Max Range: 0.8343. Min Range: -0.8343

Max Act: 0.7834. Min Act: -0.0000

Data Index: 1746289 (The Pile)

Max Activating Token Index: 218

Text #3

Max Range: 0.8343. Min Range: -0.8343

Max Act: 0.7464. Min Act: -0.0000

Data Index: 922837 (The Pile)

Max Activating Token Index: 14

Text #4

Max Range: 0.8343. Min Range: -0.8343

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1836539 (The Pile)

Max Activating Token Index: 89

Text #5

Max Range: 0.8343. Min Range: -0.8343

Max Act: 0.7078. Min Act: -0.0000

Data Index: 1839137 (The Pile)

Max Activating Token Index: 413

Text #6

Max Range: 0.8343. Min Range: -0.8343

Max Act: 0.6553. Min Act: -0.0000

Data Index: 1886840 (The Pile)

Max Activating Token Index: 837

Text #7

Max Range: 0.8343. Min Range: -0.8343

Max Act: 0.7330. Min Act: -0.0000

Data Index: 1502823 (The Pile)

Max Activating Token Index: 929

Text #8

Max Range: 0.8343. Min Range: -0.8343

Max Act: 0.7033. Min Act: -0.0000

Data Index: 1174147 (The Pile)

Max Activating Token Index: 299

Text #9

Max Range: 0.8343. Min Range: -0.8343

Max Act: 0.6764. Min Act: -0.0000

Data Index: 395714 (The Pile)

Max Activating Token Index: 325

Text #10

Max Range: 0.8343. Min Range: -0.8343

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1396145 (The Pile)

Max Activating Token Index: 630

Text #11

Max Range: 0.8343. Min Range: -0.8343

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1089334 (The Pile)

Max Activating Token Index: 556

Text #12

Max Range: 0.8343. Min Range: -0.8343

Max Act: 0.6587. Min Act: -0.0000

Data Index: 850936 (The Pile)

Max Activating Token Index: 832

Text #13

Max Range: 0.8343. Min Range: -0.8343

Max Act: 0.6338. Min Act: 0.0000

Data Index: 21636 (The Pile)

Max Activating Token Index: 385

Text #14

Max Range: 0.8343. Min Range: -0.8343

Max Act: 0.6260. Min Act: -0.0000

Data Index: 826033 (The Pile)

Max Activating Token Index: 862

Text #15

Max Range: 0.8343. Min Range: -0.8343

Max Act: 0.6044. Min Act: -0.0000

Data Index: 465264 (The Pile)

Max Activating Token Index: 435

Text #16

Max Range: 0.8343. Min Range: -0.8343

Max Act: 0.5803. Min Act: -0.0000

Data Index: 1901179 (The Pile)

Max Activating Token Index: 214

Text #17

Max Range: 0.8343. Min Range: -0.8343

Max Act: 0.6448. Min Act: -0.0000

Data Index: 345603 (The Pile)

Max Activating Token Index: 942

Text #18

Max Range: 0.8343. Min Range: -0.8343

Max Act: 0.6285. Min Act: -0.0000

Data Index: 799994 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 0.8343. Min Range: -0.8343

Max Act: 0.5762. Min Act: -0.0000

Data Index: 1601332 (The Pile)

Max Activating Token Index: 612