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

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

Neuron 3567 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2588. Min Act: -0.0000

Data Index: 129237 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2345. Min Act: -0.0000

Data Index: 84020 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1989. Min Act: -0.0000

Data Index: 471037 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2104. Min Act: -0.0000

Data Index: 1256972 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1958. Min Act: -0.0000

Data Index: 276811 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1957. Min Act: -0.0000

Data Index: 399687 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1986. Min Act: -0.0000

Data Index: 274614 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1952. Min Act: -0.0000

Data Index: 250640 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1955. Min Act: -0.0000

Data Index: 588960 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1109004 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1932. Min Act: -0.0000

Data Index: 853488 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1780. Min Act: -0.0000

Data Index: 392728 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1786. Min Act: -0.0000

Data Index: 880065 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1653. Min Act: -0.0000

Data Index: 337486 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1303612 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1591. Min Act: -0.0000

Data Index: 433829 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1582. Min Act: -0.0000

Data Index: 836814 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1632. Min Act: -0.0000

Data Index: 936553 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1555. Min Act: -0.0000

Data Index: 1279823 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1537. Min Act: -0.0000

Data Index: 99775 (C4 (Web Text))

Max Activating Token Index: 194