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

Dataset: The Pile

Neuron 2476 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: 0.5402. Min Range: -0.5402

Max Act: 0.5402. Min Act: -0.0000

Data Index: 782275 (The Pile)

Max Activating Token Index: 219

Text #1

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3565. Min Act: -0.0000

Data Index: 555467 (The Pile)

Max Activating Token Index: 946

Text #2

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3270. Min Act: -0.0000

Data Index: 1834502 (The Pile)

Max Activating Token Index: 614

Text #3

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1370728 (The Pile)

Max Activating Token Index: 547

Text #4

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.2899. Min Act: -0.0000

Data Index: 1756701 (The Pile)

Max Activating Token Index: 381

Text #5

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3087. Min Act: -0.0000

Data Index: 1952648 (The Pile)

Max Activating Token Index: 260

Text #6

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1034714 (The Pile)

Max Activating Token Index: 551

Text #7

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.2851. Min Act: -0.0000

Data Index: 906741 (The Pile)

Max Activating Token Index: 559

Text #8

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1344014 (The Pile)

Max Activating Token Index: 553

Text #9

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1283515 (The Pile)

Max Activating Token Index: 838

Text #10

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.2833. Min Act: -0.0000

Data Index: 39529 (The Pile)

Max Activating Token Index: 783

Text #11

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1220011 (The Pile)

Max Activating Token Index: 804

Text #12

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1086464 (The Pile)

Max Activating Token Index: 853

Text #13

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.2356. Min Act: -0.0000

Data Index: 548854 (The Pile)

Max Activating Token Index: 102

Text #14

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.2427. Min Act: -0.0000

Data Index: 150425 (The Pile)

Max Activating Token Index: 159

Text #15

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.2437. Min Act: -0.0000

Data Index: 1429122 (The Pile)

Max Activating Token Index: 392

Text #16

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.2469. Min Act: -0.0000

Data Index: 1456579 (The Pile)

Max Activating Token Index: 802

Text #17

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.2229. Min Act: -0.0000

Data Index: 1354468 (The Pile)

Max Activating Token Index: 97

Text #18

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.2354. Min Act: -0.0000

Data Index: 83837 (The Pile)

Max Activating Token Index: 528

Text #19

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.2118. Min Act: -0.0000

Data Index: 1827615 (The Pile)

Max Activating Token Index: 897