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

Dataset: The Pile

Neuron 864 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: 1.2413. Min Range: -1.2413

Max Act: 1.2413. Min Act: -0.0000

Data Index: 707444 (The Pile)

Max Activating Token Index: 522

Text #1

Max Range: 1.2413. Min Range: -1.2413

Max Act: 1.2216. Min Act: -0.0000

Data Index: 838803 (The Pile)

Max Activating Token Index: 959

Text #2

Max Range: 1.2413. Min Range: -1.2413

Max Act: 1.1076. Min Act: -0.0000

Data Index: 303550 (The Pile)

Max Activating Token Index: 616

Text #3

Max Range: 1.2413. Min Range: -1.2413

Max Act: 1.1242. Min Act: -0.0000

Data Index: 1576310 (The Pile)

Max Activating Token Index: 383

Text #4

Max Range: 1.2413. Min Range: -1.2413

Max Act: 1.0119. Min Act: -0.0000

Data Index: 495576 (The Pile)

Max Activating Token Index: 323

Text #5

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.9076. Min Act: -0.0000

Data Index: 1225111 (The Pile)

Max Activating Token Index: 115

Text #6

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.9153. Min Act: -0.0000

Data Index: 22518 (The Pile)

Max Activating Token Index: 763

Text #7

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.9696. Min Act: -0.0000

Data Index: 1782176 (The Pile)

Max Activating Token Index: 671

Text #8

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.9181. Min Act: -0.0000

Data Index: 205651 (The Pile)

Max Activating Token Index: 730

Text #9

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.9558. Min Act: -0.0000

Data Index: 658406 (The Pile)

Max Activating Token Index: 334

Text #10

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.7825. Min Act: -0.0000

Data Index: 933375 (The Pile)

Max Activating Token Index: 662

Text #11

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.9181. Min Act: -0.0000

Data Index: 1057836 (The Pile)

Max Activating Token Index: 270

Text #12

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.8641. Min Act: -0.0000

Data Index: 1696647 (The Pile)

Max Activating Token Index: 797

Text #13

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.8830. Min Act: -0.0000

Data Index: 1024003 (The Pile)

Max Activating Token Index: 169

Text #14

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.8901. Min Act: -0.0000

Data Index: 319845 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.8620. Min Act: -0.0000

Data Index: 228704 (The Pile)

Max Activating Token Index: 199

Text #16

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.9150. Min Act: -0.0000

Data Index: 1835729 (The Pile)

Max Activating Token Index: 795

Text #17

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.8746. Min Act: -0.0000

Data Index: 720988 (The Pile)

Max Activating Token Index: 195

Text #18

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.8815. Min Act: -0.0000

Data Index: 1439724 (The Pile)

Max Activating Token Index: 94

Text #19

Max Range: 1.2413. Min Range: -1.2413

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1206087 (The Pile)

Max Activating Token Index: 175