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

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

Neuron 2630 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.3469. Min Act: -0.0000

Data Index: 1465922 (Python Code)

Max Activating Token Index: 247

Text #1

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1407555 (Python Code)

Max Activating Token Index: 977

Text #2

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.3373. Min Act: -0.0000

Data Index: 1507525 (Python Code)

Max Activating Token Index: 886

Text #3

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.3156. Min Act: -0.0001

Data Index: 1185435 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1626826 (Python Code)

Max Activating Token Index: 937

Text #5

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2896. Min Act: -0.0000

Data Index: 1397262 (Python Code)

Max Activating Token Index: 48

Text #6

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2963. Min Act: -0.0001

Data Index: 926495 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2889. Min Act: -0.0001

Data Index: 1007763 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.3161. Min Act: -0.0001

Data Index: 869192 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2954. Min Act: -0.0000

Data Index: 1593634 (Python Code)

Max Activating Token Index: 583

Text #10

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2724. Min Act: -0.0001

Data Index: 871901 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2684. Min Act: -0.0001

Data Index: 1022892 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1423655 (Python Code)

Max Activating Token Index: 597

Text #13

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2832. Min Act: -0.0001

Data Index: 685301 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1547365 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2825. Min Act: -0.0000

Data Index: 639014 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2730. Min Act: -0.0001

Data Index: 902866 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2787. Min Act: -0.0001

Data Index: 1619311 (Python Code)

Max Activating Token Index: 613

Text #18

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2596. Min Act: -0.0001

Data Index: 319236 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.3491. Min Range: -0.3491

Max Act: 0.2729. Min Act: -0.0000

Data Index: 1567344 (Python Code)

Max Activating Token Index: 285