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

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

Neuron 2111 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: 0.0632. Min Range: -0.0632

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1171128 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0577. Min Act: -0.0002

Data Index: 205010 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0592. Min Act: -0.0002

Data Index: 286104 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0585. Min Act: -0.0002

Data Index: 636156 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0603. Min Act: -0.0002

Data Index: 809265 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0593. Min Act: -0.0002

Data Index: 213753 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0562. Min Act: -0.0002

Data Index: 109043 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0575. Min Act: -0.0002

Data Index: 249509 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0520. Min Act: -0.0002

Data Index: 102160 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0518. Min Act: -0.0002

Data Index: 440966 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0522. Min Act: -0.0002

Data Index: 582684 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1129301 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0533. Min Act: -0.0002

Data Index: 413332 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1307759 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1154384 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0525. Min Act: -0.0002

Data Index: 432120 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1083036 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0523. Min Act: -0.0002

Data Index: 151300 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0514. Min Act: -0.0002

Data Index: 548937 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1355790 (C4 (Web Text))

Max Activating Token Index: 384