Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 918 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3595. Min Act: 0.0000

Data Index: 1236624 (The Pile)

Max Activating Token Index: 161

Text #1

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3023. Min Act: -0.0000

Data Index: 1492538 (The Pile)

Max Activating Token Index: 152

Text #2

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3292. Min Act: -0.0000

Data Index: 469639 (The Pile)

Max Activating Token Index: 180

Text #3

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2772. Min Act: -0.0001

Data Index: 1306746 (The Pile)

Max Activating Token Index: 351

Text #4

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2758. Min Act: -0.0001

Data Index: 1129357 (The Pile)

Max Activating Token Index: 334

Text #5

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2552. Min Act: -0.0000

Data Index: 1820226 (The Pile)

Max Activating Token Index: 300

Text #6

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2512. Min Act: -0.0000

Data Index: 884782 (The Pile)

Max Activating Token Index: 215

Text #7

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2521. Min Act: -0.0000

Data Index: 1293547 (The Pile)

Max Activating Token Index: 126

Text #8

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2577. Min Act: -0.0000

Data Index: 209164 (The Pile)

Max Activating Token Index: 594

Text #9

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2538. Min Act: -0.0000

Data Index: 159719 (The Pile)

Max Activating Token Index: 570

Text #10

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2284. Min Act: -0.0001

Data Index: 831231 (The Pile)

Max Activating Token Index: 849

Text #11

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2628. Min Act: -0.0000

Data Index: 131656 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2507. Min Act: -0.0000

Data Index: 798220 (The Pile)

Max Activating Token Index: 171

Text #13

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2389. Min Act: -0.0000

Data Index: 485352 (The Pile)

Max Activating Token Index: 622

Text #14

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1716133 (The Pile)

Max Activating Token Index: 588

Text #15

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2474. Min Act: -0.0001

Data Index: 1636190 (The Pile)

Max Activating Token Index: 647

Text #16

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2481. Min Act: -0.0000

Data Index: 966564 (The Pile)

Max Activating Token Index: 86

Text #17

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2437. Min Act: -0.0000

Data Index: 1022098 (The Pile)

Max Activating Token Index: 585

Text #18

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2421. Min Act: -0.0000

Data Index: 1317568 (The Pile)

Max Activating Token Index: 219

Text #19

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2257. Min Act: -0.0001

Data Index: 964684 (The Pile)

Max Activating Token Index: 626