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

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

Neuron 183 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1160. Min Act: -0.0001

Data Index: 140912 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1121. Min Act: -0.0001

Data Index: 1274612 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1121. Min Act: -0.0001

Data Index: 806388 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1085. Min Act: -0.0001

Data Index: 662828 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1024. Min Act: -0.0001

Data Index: 316938 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1017. Min Act: -0.0001

Data Index: 87970 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1017. Min Act: -0.0001

Data Index: 76081 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0967. Min Act: -0.0001

Data Index: 475395 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1023791 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0927. Min Act: -0.0001

Data Index: 35181 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0925. Min Act: -0.0001

Data Index: 1116597 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0961. Min Act: -0.0001

Data Index: 100384 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0924. Min Act: -0.0001

Data Index: 177717 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0906. Min Act: -0.0001

Data Index: 218521 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0900. Min Act: -0.0001

Data Index: 1126097 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0991. Min Act: -0.0001

Data Index: 781952 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0883. Min Act: -0.0001

Data Index: 945140 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0849. Min Act: -0.0001

Data Index: 606620 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1109868 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0872. Min Act: -0.0001

Data Index: 829593 (C4 (Web Text))

Max Activating Token Index: 522