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

Dataset: The Pile

Neuron 38 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.8213. Min Act: -0.0000

Data Index: 1665739 (The Pile)

Max Activating Token Index: 821

Text #1

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.5376. Min Act: -0.0000

Data Index: 1569085 (The Pile)

Max Activating Token Index: 875

Text #2

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.7095. Min Act: -0.0000

Data Index: 1430687 (The Pile)

Max Activating Token Index: 664

Text #3

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.6493. Min Act: -0.0000

Data Index: 1345290 (The Pile)

Max Activating Token Index: 619

Text #4

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.6416. Min Act: -0.0000

Data Index: 581077 (The Pile)

Max Activating Token Index: 232

Text #5

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.6641. Min Act: -0.0000

Data Index: 725717 (The Pile)

Max Activating Token Index: 381

Text #6

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.5714. Min Act: -0.0000

Data Index: 711282 (The Pile)

Max Activating Token Index: 524

Text #7

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.6155. Min Act: -0.0000

Data Index: 814029 (The Pile)

Max Activating Token Index: 743

Text #8

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.5540. Min Act: -0.0000

Data Index: 1791489 (The Pile)

Max Activating Token Index: 654

Text #9

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.5094. Min Act: -0.0000

Data Index: 36771 (The Pile)

Max Activating Token Index: 355

Text #10

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.5018. Min Act: -0.0000

Data Index: 1690137 (The Pile)

Max Activating Token Index: 587

Text #11

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.4790. Min Act: -0.0000

Data Index: 1201934 (The Pile)

Max Activating Token Index: 701

Text #12

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.4652. Min Act: -0.0000

Data Index: 435101 (The Pile)

Max Activating Token Index: 572

Text #13

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.5560. Min Act: -0.0000

Data Index: 629017 (The Pile)

Max Activating Token Index: 720

Text #14

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.4821. Min Act: -0.0000

Data Index: 438670 (The Pile)

Max Activating Token Index: 837

Text #15

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.5157. Min Act: -0.0000

Data Index: 132457 (The Pile)

Max Activating Token Index: 633

Text #16

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.4671. Min Act: 0.0000

Data Index: 609370 (The Pile)

Max Activating Token Index: 655

Text #17

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.4079. Min Act: -0.0000

Data Index: 1875761 (The Pile)

Max Activating Token Index: 586

Text #18

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.3977. Min Act: -0.0000

Data Index: 814313 (The Pile)

Max Activating Token Index: 695

Text #19

Max Range: 1.8213. Min Range: -1.8213

Max Act: 1.3820. Min Act: -0.0000

Data Index: 298212 (The Pile)

Max Activating Token Index: 390