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

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

Neuron 2561 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.5914. Min Act: -0.0000

Data Index: 1371073 (Python Code)

Max Activating Token Index: 765

Text #1

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4104. Min Act: -0.0000

Data Index: 113365 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4275. Min Act: -0.0000

Data Index: 761368 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.3569. Min Act: -0.0000

Data Index: 311386 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.3514. Min Act: -0.0000

Data Index: 1369919 (Python Code)

Max Activating Token Index: 695

Text #5

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1455524 (Python Code)

Max Activating Token Index: 303

Text #6

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.3726. Min Act: -0.0000

Data Index: 1525638 (Python Code)

Max Activating Token Index: 738

Text #7

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.3159. Min Act: -0.0000

Data Index: 1629465 (Python Code)

Max Activating Token Index: 733

Text #8

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.3123. Min Act: -0.0000

Data Index: 246505 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1562330 (Python Code)

Max Activating Token Index: 457

Text #10

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2967. Min Act: -0.0000

Data Index: 910063 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1466696 (Python Code)

Max Activating Token Index: 507

Text #12

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1543285 (Python Code)

Max Activating Token Index: 990

Text #13

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2542. Min Act: -0.0000

Data Index: 1461160 (Python Code)

Max Activating Token Index: 735

Text #14

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2840. Min Act: -0.0000

Data Index: 48222 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2851. Min Act: -0.0000

Data Index: 1432327 (Python Code)

Max Activating Token Index: 841

Text #16

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2922. Min Act: -0.0000

Data Index: 1491264 (Python Code)

Max Activating Token Index: 482

Text #17

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1633551 (Python Code)

Max Activating Token Index: 946

Text #18

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1558111 (Python Code)

Max Activating Token Index: 222

Text #19

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1625469 (Python Code)

Max Activating Token Index: 875