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

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

Neuron 2890 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1145. Min Act: -0.0001

Data Index: 382295 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1182. Min Act: -0.0001

Data Index: 116529 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1320. Min Act: -0.0001

Data Index: 1318733 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1211. Min Act: -0.0001

Data Index: 877998 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1183. Min Act: -0.0001

Data Index: 247654 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1189. Min Act: -0.0001

Data Index: 992886 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1188. Min Act: -0.0001

Data Index: 871534 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1065. Min Act: -0.0001

Data Index: 253305 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1038. Min Act: -0.0001

Data Index: 600480 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1069. Min Act: -0.0001

Data Index: 114506 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1031. Min Act: -0.0001

Data Index: 413817 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1052. Min Act: -0.0001

Data Index: 954316 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0961. Min Act: -0.0001

Data Index: 17847 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1066. Min Act: -0.0001

Data Index: 952535 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1053. Min Act: -0.0001

Data Index: 61350 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1039. Min Act: -0.0001

Data Index: 91723 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1001. Min Act: -0.0001

Data Index: 763500 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1032795 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1027. Min Act: -0.0001

Data Index: 1250344 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0988. Min Act: -0.0001

Data Index: 637129 (C4 (Web Text))

Max Activating Token Index: 700