Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1697 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1953. Min Act: -0.0003

Data Index: 493537 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1828. Min Act: -0.0003

Data Index: 819553 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1774. Min Act: -0.0003

Data Index: 373760 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1729. Min Act: -0.0003

Data Index: 1283401 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1789. Min Act: -0.0003

Data Index: 3594 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1661. Min Act: -0.0003

Data Index: 1089440 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1716. Min Act: -0.0003

Data Index: 62423 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1490. Min Act: -0.0003

Data Index: 1197835 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1676. Min Act: -0.0003

Data Index: 646453 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1610. Min Act: -0.0003

Data Index: 925793 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1576. Min Act: -0.0003

Data Index: 283702 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1510. Min Act: -0.0003

Data Index: 1268932 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1512. Min Act: -0.0003

Data Index: 630407 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1441. Min Act: -0.0003

Data Index: 871625 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1490. Min Act: -0.0003

Data Index: 298121 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1426. Min Act: -0.0003

Data Index: 1047298 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1667. Min Act: -0.0003

Data Index: 1199552 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1472. Min Act: -0.0003

Data Index: 467735 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1322. Min Act: -0.0003

Data Index: 767965 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1444. Min Act: -0.0003

Data Index: 431127 (C4 (Web Text))

Max Activating Token Index: 578