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

Dataset: The Pile

Neuron 3919 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: 0.7488. Min Range: -0.7488

Max Act: 0.6878. Min Act: 0.0000

Data Index: 1154883 (The Pile)

Max Activating Token Index: 187

Text #1

Max Range: 0.7488. Min Range: -0.7488

Max Act: 0.7488. Min Act: -0.0000

Data Index: 7581 (The Pile)

Max Activating Token Index: 349

Text #2

Max Range: 0.7488. Min Range: -0.7488

Max Act: 0.6415. Min Act: -0.0001

Data Index: 187550 (The Pile)

Max Activating Token Index: 674

Text #3

Max Range: 0.7488. Min Range: -0.7488

Max Act: 0.7056. Min Act: -0.0000

Data Index: 774775 (The Pile)

Max Activating Token Index: 336

Text #4

Max Range: 0.7488. Min Range: -0.7488

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1517017 (The Pile)

Max Activating Token Index: 218

Text #5

Max Range: 0.7488. Min Range: -0.7488

Max Act: 0.7206. Min Act: -0.0000

Data Index: 978689 (The Pile)

Max Activating Token Index: 1008

Text #6

Max Range: 0.7488. Min Range: -0.7488

Max Act: 0.6236. Min Act: -0.0000

Data Index: 183881 (The Pile)

Max Activating Token Index: 549

Text #7

Max Range: 0.7488. Min Range: -0.7488

Max Act: 0.6904. Min Act: -0.0000

Data Index: 1626569 (The Pile)

Max Activating Token Index: 656

Text #8

Max Range: 0.7488. Min Range: -0.7488

Max Act: 0.6203. Min Act: -0.0000

Data Index: 159792 (The Pile)

Max Activating Token Index: 435

Text #9

Max Range: 0.7488. Min Range: -0.7488

Max Act: 0.6422. Min Act: -0.0000

Data Index: 256121 (The Pile)

Max Activating Token Index: 314

Text #10

Max Range: 0.7488. Min Range: -0.7488

Max Act: 0.6430. Min Act: -0.0000

Data Index: 423300 (The Pile)

Max Activating Token Index: 442

Text #11

Max Range: 0.7488. Min Range: -0.7488

Max Act: 0.6020. Min Act: -0.0000

Data Index: 315630 (The Pile)

Max Activating Token Index: 184

Text #12

Max Range: 0.7488. Min Range: -0.7488

Max Act: 0.6298. Min Act: -0.0000

Data Index: 468375 (The Pile)

Max Activating Token Index: 264

Text #13

Max Range: 0.7488. Min Range: -0.7488

Max Act: 0.6864. Min Act: -0.0000

Data Index: 746701 (The Pile)

Max Activating Token Index: 444

Text #14

Max Range: 0.7488. Min Range: -0.7488

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1330723 (The Pile)

Max Activating Token Index: 452

Text #15

Max Range: 0.7488. Min Range: -0.7488

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1626265 (The Pile)

Max Activating Token Index: 809

Text #16

Max Range: 0.7488. Min Range: -0.7488

Max Act: 0.6797. Min Act: -0.0000

Data Index: 215854 (The Pile)

Max Activating Token Index: 113

Text #17

Max Range: 0.7488. Min Range: -0.7488

Max Act: 0.6312. Min Act: -0.0000

Data Index: 1700359 (The Pile)

Max Activating Token Index: 234

Text #18

Max Range: 0.7488. Min Range: -0.7488

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1589520 (The Pile)

Max Activating Token Index: 615

Text #19

Max Range: 0.7488. Min Range: -0.7488

Max Act: 0.6297. Min Act: -0.0000

Data Index: 726675 (The Pile)

Max Activating Token Index: 354