Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4923 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3804. Min Act: -0.0000

Data Index: 624535 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3632. Min Act: -0.0000

Data Index: 230032 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3404. Min Act: -0.0000

Data Index: 1425568 (Python Code)

Max Activating Token Index: 443

Text #3

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3356. Min Act: -0.0000

Data Index: 741122 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3323. Min Act: -0.0000

Data Index: 880386 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3128. Min Act: -0.0000

Data Index: 813174 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2992. Min Act: -0.0000

Data Index: 1538752 (Python Code)

Max Activating Token Index: 829

Text #7

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2997. Min Act: -0.0000

Data Index: 1142986 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3091. Min Act: -0.0000

Data Index: 1490046 (Python Code)

Max Activating Token Index: 481

Text #9

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2706. Min Act: -0.0000

Data Index: 893026 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2862. Min Act: -0.0000

Data Index: 1013814 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2832. Min Act: -0.0000

Data Index: 797526 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1655143 (Python Code)

Max Activating Token Index: 445

Text #13

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2861. Min Act: -0.0000

Data Index: 110901 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2781. Min Act: -0.0000

Data Index: 413929 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2763. Min Act: -0.0000

Data Index: 251721 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2775. Min Act: -0.0000

Data Index: 173402 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2870. Min Act: -0.0000

Data Index: 16596 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2750. Min Act: -0.0000

Data Index: 1023505 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2671. Min Act: -0.0000

Data Index: 1095254 (C4 (Web Text))

Max Activating Token Index: 247