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

Dataset: The Pile

Neuron 3510 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6461. Min Range: -0.6461

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1331687 (The Pile)

Max Activating Token Index: 679

Text #1

Max Range: 0.6461. Min Range: -0.6461

Max Act: 0.5522. Min Act: -0.0000

Data Index: 1873710 (The Pile)

Max Activating Token Index: 108

Text #2

Max Range: 0.6461. Min Range: -0.6461

Max Act: 0.4270. Min Act: 0.0000

Data Index: 1786216 (The Pile)

Max Activating Token Index: 138

Text #3

Max Range: 0.6461. Min Range: -0.6461

Max Act: 0.4266. Min Act: 0.0000

Data Index: 1477482 (The Pile)

Max Activating Token Index: 725

Text #4

Max Range: 0.6461. Min Range: -0.6461

Max Act: 0.3907. Min Act: 0.0000

Data Index: 1380927 (The Pile)

Max Activating Token Index: 506

Text #5

Max Range: 0.6461. Min Range: -0.6461

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1239978 (The Pile)

Max Activating Token Index: 629

Text #6

Max Range: 0.6461. Min Range: -0.6461

Max Act: 0.3460. Min Act: -0.0000

Data Index: 931226 (The Pile)

Max Activating Token Index: 785

Text #7

Max Range: 0.6461. Min Range: -0.6461

Max Act: 0.3746. Min Act: -0.0000

Data Index: 114203 (The Pile)

Max Activating Token Index: 803

Text #8

Max Range: 0.6461. Min Range: -0.6461

Max Act: 0.3155. Min Act: -0.0000

Data Index: 199028 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.6461. Min Range: -0.6461

Max Act: 0.3579. Min Act: -0.0000

Data Index: 328949 (The Pile)

Max Activating Token Index: 207

Text #10

Max Range: 0.6461. Min Range: -0.6461

Max Act: 0.3740. Min Act: -0.0000

Data Index: 971868 (The Pile)

Max Activating Token Index: 55

Text #11

Max Range: 0.6461. Min Range: -0.6461

Max Act: 0.3248. Min Act: -0.0000

Data Index: 1857099 (The Pile)

Max Activating Token Index: 633

Text #12

Max Range: 0.6461. Min Range: -0.6461

Max Act: 0.3481. Min Act: 0.0000

Data Index: 460695 (The Pile)

Max Activating Token Index: 455

Text #13

Max Range: 0.6461. Min Range: -0.6461

Max Act: 0.3111. Min Act: -0.0000

Data Index: 1445271 (The Pile)

Max Activating Token Index: 857

Text #14

Max Range: 0.6461. Min Range: -0.6461

Max Act: 0.2786. Min Act: 0.0000

Data Index: 464306 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.6461. Min Range: -0.6461

Max Act: 0.2881. Min Act: -0.0000

Data Index: 1123310 (The Pile)

Max Activating Token Index: 378

Text #16

Max Range: 0.6461. Min Range: -0.6461

Max Act: 0.2908. Min Act: -0.0000

Data Index: 772953 (The Pile)

Max Activating Token Index: 409

Text #17

Max Range: 0.6461. Min Range: -0.6461

Max Act: 0.3000. Min Act: -0.0000

Data Index: 1218718 (The Pile)

Max Activating Token Index: 352

Text #18

Max Range: 0.6461. Min Range: -0.6461

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1165086 (The Pile)

Max Activating Token Index: 709

Text #19

Max Range: 0.6461. Min Range: -0.6461

Max Act: 0.2882. Min Act: 0.0000

Data Index: 1459633 (The Pile)

Max Activating Token Index: 667