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

Dataset: The Pile

Neuron 3050 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1175250 (The Pile)

Max Activating Token Index: 250

Text #1

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.8409. Min Act: -0.0000

Data Index: 1179504 (The Pile)

Max Activating Token Index: 463

Text #2

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.7949. Min Act: -0.0000

Data Index: 401595 (The Pile)

Max Activating Token Index: 649

Text #3

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.8180. Min Act: -0.0000

Data Index: 1573864 (The Pile)

Max Activating Token Index: 411

Text #4

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.8164. Min Act: -0.0000

Data Index: 1604529 (The Pile)

Max Activating Token Index: 1001

Text #5

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.8259. Min Act: -0.0000

Data Index: 569632 (The Pile)

Max Activating Token Index: 797

Text #6

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.7834. Min Act: -0.0000

Data Index: 464456 (The Pile)

Max Activating Token Index: 475

Text #7

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.8022. Min Act: -0.0000

Data Index: 272488 (The Pile)

Max Activating Token Index: 493

Text #8

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.8003. Min Act: -0.0000

Data Index: 756696 (The Pile)

Max Activating Token Index: 741

Text #9

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.7528. Min Act: -0.0000

Data Index: 1080260 (The Pile)

Max Activating Token Index: 1022

Text #10

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.7315. Min Act: -0.0000

Data Index: 356334 (The Pile)

Max Activating Token Index: 473

Text #11

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.6990. Min Act: -0.0000

Data Index: 168237 (The Pile)

Max Activating Token Index: 811

Text #12

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.7313. Min Act: -0.0000

Data Index: 1514820 (The Pile)

Max Activating Token Index: 536

Text #13

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1572730 (The Pile)

Max Activating Token Index: 964

Text #14

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.6647. Min Act: -0.0000

Data Index: 899508 (The Pile)

Max Activating Token Index: 882

Text #15

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.7413. Min Act: -0.0000

Data Index: 1859401 (The Pile)

Max Activating Token Index: 574

Text #16

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.6902. Min Act: -0.0000

Data Index: 270040 (The Pile)

Max Activating Token Index: 599

Text #17

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.7578. Min Act: -0.0000

Data Index: 1816088 (The Pile)

Max Activating Token Index: 187

Text #18

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.7301. Min Act: -0.0000

Data Index: 1338918 (The Pile)

Max Activating Token Index: 208

Text #19

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1359882 (The Pile)

Max Activating Token Index: 785