Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 535 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1181. Min Act: -0.0001

Data Index: 571749 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1111. Min Act: -0.0001

Data Index: 849887 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1074. Min Act: -0.0001

Data Index: 984189 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1003. Min Act: -0.0001

Data Index: 923065 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1016. Min Act: -0.0001

Data Index: 139025 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1008. Min Act: -0.0000

Data Index: 78696 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0963. Min Act: -0.0001

Data Index: 368900 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1001. Min Act: -0.0001

Data Index: 187709 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1328131 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0948. Min Act: -0.0001

Data Index: 243655 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0959. Min Act: -0.0001

Data Index: 209261 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0960. Min Act: -0.0001

Data Index: 455047 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0942. Min Act: -0.0001

Data Index: 146444 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0969. Min Act: -0.0001

Data Index: 1082034 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0936. Min Act: -0.0001

Data Index: 522429 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0900. Min Act: -0.0001

Data Index: 318323 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0933. Min Act: -0.0001

Data Index: 290607 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0889. Min Act: -0.0001

Data Index: 1245059 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0953. Min Act: -0.0001

Data Index: 272690 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0920. Min Act: -0.0001

Data Index: 399374 (C4 (Web Text))

Max Activating Token Index: 940