Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3830 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0579. Min Act: -0.0002

Data Index: 273856 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0573. Min Act: -0.0002

Data Index: 181051 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0531. Min Act: -0.0002

Data Index: 369439 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0537. Min Act: -0.0002

Data Index: 235641 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0621. Min Act: -0.0001

Data Index: 790925 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0552. Min Act: -0.0002

Data Index: 322953 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1231952 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0540. Min Act: -0.0002

Data Index: 242947 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0541. Min Act: -0.0001

Data Index: 1275138 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1009540 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0497. Min Act: -0.0001

Data Index: 1058171 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0483. Min Act: -0.0002

Data Index: 213983 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0430. Min Act: -0.0002

Data Index: 492438 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0460. Min Act: -0.0002

Data Index: 501835 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0440. Min Act: -0.0002

Data Index: 696801 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0462. Min Act: -0.0001

Data Index: 555070 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0442. Min Act: -0.0001

Data Index: 250069 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0410. Min Act: -0.0002

Data Index: 431315 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0409. Min Act: -0.0002

Data Index: 646088 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0407. Min Act: -0.0001

Data Index: 1250122 (C4 (Web Text))

Max Activating Token Index: 71