Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3872 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.4043. Min Act: -0.0002

Data Index: 1242940 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.4055. Min Act: -0.0002

Data Index: 130528 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3452. Min Act: -0.0002

Data Index: 527761 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3523. Min Act: -0.0002

Data Index: 231004 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3367. Min Act: -0.0002

Data Index: 1385855 (Python Code)

Max Activating Token Index: 661

Text #5

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3148. Min Act: -0.0002

Data Index: 1226641 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.2819. Min Act: -0.0002

Data Index: 1653595 (Python Code)

Max Activating Token Index: 369

Text #7

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.2855. Min Act: -0.0002

Data Index: 1612615 (Python Code)

Max Activating Token Index: 414

Text #8

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.2608. Min Act: -0.0002

Data Index: 1655850 (Python Code)

Max Activating Token Index: 408

Text #9

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.2597. Min Act: -0.0002

Data Index: 1376696 (Python Code)

Max Activating Token Index: 442

Text #10

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.2317. Min Act: -0.0002

Data Index: 139576 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.2476. Min Act: -0.0002

Data Index: 217170 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.2430. Min Act: -0.0002

Data Index: 154735 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.2530. Min Act: -0.0002

Data Index: 1370868 (Python Code)

Max Activating Token Index: 66

Text #14

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.2583. Min Act: -0.0002

Data Index: 1555679 (Python Code)

Max Activating Token Index: 256

Text #15

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.2477. Min Act: -0.0002

Data Index: 1591047 (Python Code)

Max Activating Token Index: 918

Text #16

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.2453. Min Act: -0.0002

Data Index: 1396162 (Python Code)

Max Activating Token Index: 444

Text #17

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.2459. Min Act: -0.0002

Data Index: 1384516 (Python Code)

Max Activating Token Index: 808

Text #18

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.2525. Min Act: -0.0002

Data Index: 1066283 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.2527. Min Act: -0.0002

Data Index: 1549816 (Python Code)

Max Activating Token Index: 479