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

Dataset: The Pile

Neuron 3950 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: 3.6760. Min Range: -3.6760

Max Act: 3.6760. Min Act: -0.0000

Data Index: 995789 (The Pile)

Max Activating Token Index: 688

Text #1

Max Range: 3.6760. Min Range: -3.6760

Max Act: 2.6401. Min Act: -0.0000

Data Index: 837558 (The Pile)

Max Activating Token Index: 706

Text #2

Max Range: 3.6760. Min Range: -3.6760

Max Act: 2.9015. Min Act: -0.0000

Data Index: 1821664 (The Pile)

Max Activating Token Index: 1016

Text #3

Max Range: 3.6760. Min Range: -3.6760

Max Act: 2.9796. Min Act: -0.0000

Data Index: 1545647 (The Pile)

Max Activating Token Index: 395

Text #4

Max Range: 3.6760. Min Range: -3.6760

Max Act: 3.1001. Min Act: -0.0000

Data Index: 1317362 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 3.6760. Min Range: -3.6760

Max Act: 2.9475. Min Act: -0.0000

Data Index: 886654 (The Pile)

Max Activating Token Index: 539

Text #6

Max Range: 3.6760. Min Range: -3.6760

Max Act: 2.8417. Min Act: -0.0000

Data Index: 227943 (The Pile)

Max Activating Token Index: 811

Text #7

Max Range: 3.6760. Min Range: -3.6760

Max Act: 2.7699. Min Act: -0.0000

Data Index: 1236130 (The Pile)

Max Activating Token Index: 469

Text #8

Max Range: 3.6760. Min Range: -3.6760

Max Act: 2.4911. Min Act: -0.0000

Data Index: 786739 (The Pile)

Max Activating Token Index: 783

Text #9

Max Range: 3.6760. Min Range: -3.6760

Max Act: 2.3377. Min Act: -0.0000

Data Index: 1897653 (The Pile)

Max Activating Token Index: 702

Text #10

Max Range: 3.6760. Min Range: -3.6760

Max Act: 2.5701. Min Act: -0.0000

Data Index: 1454354 (The Pile)

Max Activating Token Index: 292

Text #11

Max Range: 3.6760. Min Range: -3.6760

Max Act: 2.5400. Min Act: -0.0000

Data Index: 1186022 (The Pile)

Max Activating Token Index: 439

Text #12

Max Range: 3.6760. Min Range: -3.6760

Max Act: 2.5384. Min Act: -0.0000

Data Index: 1727049 (The Pile)

Max Activating Token Index: 713

Text #13

Max Range: 3.6760. Min Range: -3.6760

Max Act: 2.3346. Min Act: -0.0000

Data Index: 1023070 (The Pile)

Max Activating Token Index: 670

Text #14

Max Range: 3.6760. Min Range: -3.6760

Max Act: 2.4666. Min Act: -0.0000

Data Index: 783742 (The Pile)

Max Activating Token Index: 469

Text #15

Max Range: 3.6760. Min Range: -3.6760

Max Act: 2.4505. Min Act: -0.0000

Data Index: 1487349 (The Pile)

Max Activating Token Index: 96

Text #16

Max Range: 3.6760. Min Range: -3.6760

Max Act: 2.3121. Min Act: -0.0000

Data Index: 643664 (The Pile)

Max Activating Token Index: 528

Text #17

Max Range: 3.6760. Min Range: -3.6760

Max Act: 2.2931. Min Act: -0.0000

Data Index: 163157 (The Pile)

Max Activating Token Index: 653

Text #18

Max Range: 3.6760. Min Range: -3.6760

Max Act: 2.5342. Min Act: -0.0000

Data Index: 1334906 (The Pile)

Max Activating Token Index: 372

Text #19

Max Range: 3.6760. Min Range: -3.6760

Max Act: 2.0312. Min Act: -0.0000

Data Index: 1080639 (The Pile)

Max Activating Token Index: 673