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

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

Neuron 686 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1256990 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.3176. Min Act: -0.0001

Data Index: 1510418 (Python Code)

Max Activating Token Index: 988

Text #2

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2963. Min Act: -0.0000

Data Index: 595031 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2944. Min Act: -0.0001

Data Index: 1533188 (Python Code)

Max Activating Token Index: 70

Text #4

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2836. Min Act: -0.0000

Data Index: 518365 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2991. Min Act: -0.0000

Data Index: 674547 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2884. Min Act: -0.0001

Data Index: 1435459 (Python Code)

Max Activating Token Index: 266

Text #7

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2712. Min Act: -0.0000

Data Index: 505048 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2851. Min Act: -0.0001

Data Index: 1614216 (Python Code)

Max Activating Token Index: 478

Text #9

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2735. Min Act: -0.0000

Data Index: 1230850 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2730. Min Act: -0.0000

Data Index: 886397 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2801. Min Act: -0.0001

Data Index: 1414049 (Python Code)

Max Activating Token Index: 623

Text #12

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2910. Min Act: -0.0001

Data Index: 1647857 (Python Code)

Max Activating Token Index: 886

Text #13

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1016586 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2771. Min Act: -0.0000

Data Index: 16457 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2747. Min Act: -0.0001

Data Index: 1567903 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2622. Min Act: -0.0001

Data Index: 1579054 (Python Code)

Max Activating Token Index: 532

Text #17

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2704. Min Act: -0.0001

Data Index: 1393368 (Python Code)

Max Activating Token Index: 993

Text #18

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2671. Min Act: -0.0000

Data Index: 67800 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2584. Min Act: -0.0001

Data Index: 1455534 (Python Code)

Max Activating Token Index: 337