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

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

Neuron 3140 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1367. Min Act: -0.0001

Data Index: 1043730 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1140. Min Act: -0.0001

Data Index: 2240 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1060. Min Act: -0.0001

Data Index: 1197044 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1018. Min Act: -0.0001

Data Index: 1157770 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1018. Min Act: -0.0001

Data Index: 1206066 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1034. Min Act: -0.0001

Data Index: 83892 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0971. Min Act: -0.0001

Data Index: 1132204 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0918. Min Act: -0.0001

Data Index: 996188 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0926. Min Act: -0.0001

Data Index: 570000 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0822. Min Act: -0.0001

Data Index: 925624 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0928. Min Act: -0.0001

Data Index: 350457 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0831. Min Act: -0.0001

Data Index: 846253 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0845. Min Act: -0.0000

Data Index: 899267 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0779. Min Act: -0.0001

Data Index: 569146 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0820. Min Act: -0.0001

Data Index: 982429 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0777. Min Act: -0.0001

Data Index: 531276 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0791. Min Act: -0.0000

Data Index: 168850 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0860. Min Act: -0.0001

Data Index: 794267 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0820. Min Act: -0.0001

Data Index: 234155 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0822. Min Act: -0.0001

Data Index: 795656 (C4 (Web Text))

Max Activating Token Index: 189