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

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

Neuron 4966 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9683. Min Range: -0.9683

Max Act: 0.9683. Min Act: -0.0001

Data Index: 770465 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 0.9683. Min Range: -0.9683

Max Act: 0.9480. Min Act: -0.0001

Data Index: 1154856 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.9683. Min Range: -0.9683

Max Act: 0.9537. Min Act: -0.0001

Data Index: 212260 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.9683. Min Range: -0.9683

Max Act: 0.8392. Min Act: -0.0000

Data Index: 716925 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.9683. Min Range: -0.9683

Max Act: 0.8573. Min Act: -0.0001

Data Index: 1123967 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.9683. Min Range: -0.9683

Max Act: 0.8787. Min Act: -0.0001

Data Index: 1031994 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.9683. Min Range: -0.9683

Max Act: 0.8132. Min Act: -0.0001

Data Index: 743659 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.9683. Min Range: -0.9683

Max Act: 0.8556. Min Act: -0.0001

Data Index: 602161 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.9683. Min Range: -0.9683

Max Act: 0.7874. Min Act: -0.0001

Data Index: 1194597 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.9683. Min Range: -0.9683

Max Act: 0.7899. Min Act: -0.0001

Data Index: 966532 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 0.9683. Min Range: -0.9683

Max Act: 0.7643. Min Act: -0.0001

Data Index: 555223 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.9683. Min Range: -0.9683

Max Act: 0.7501. Min Act: -0.0001

Data Index: 993848 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 0.9683. Min Range: -0.9683

Max Act: 0.7110. Min Act: -0.0001

Data Index: 64579 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.9683. Min Range: -0.9683

Max Act: 0.7903. Min Act: -0.0001

Data Index: 408296 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.9683. Min Range: -0.9683

Max Act: 0.7041. Min Act: -0.0001

Data Index: 35211 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 0.9683. Min Range: -0.9683

Max Act: 0.7101. Min Act: -0.0001

Data Index: 807514 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.9683. Min Range: -0.9683

Max Act: 0.7825. Min Act: -0.0001

Data Index: 1225891 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.9683. Min Range: -0.9683

Max Act: 0.7405. Min Act: -0.0001

Data Index: 110029 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.9683. Min Range: -0.9683

Max Act: 0.7960. Min Act: -0.0001

Data Index: 1015769 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.9683. Min Range: -0.9683

Max Act: 0.7817. Min Act: -0.0000

Data Index: 714118 (C4 (Web Text))

Max Activating Token Index: 612