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

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

Neuron 1303 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5239. Min Range: -2.5239

Max Act: 2.5239. Min Act: -0.0000

Data Index: 981007 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 2.5239. Min Range: -2.5239

Max Act: 2.5054. Min Act: -0.0000

Data Index: 149222 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 2.5239. Min Range: -2.5239

Max Act: 1.5590. Min Act: -0.0000

Data Index: 984562 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 2.5239. Min Range: -2.5239

Max Act: 1.5148. Min Act: -0.0000

Data Index: 58711 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 2.5239. Min Range: -2.5239

Max Act: 1.6464. Min Act: -0.0000

Data Index: 449918 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 2.5239. Min Range: -2.5239

Max Act: 1.5979. Min Act: -0.0000

Data Index: 460579 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 2.5239. Min Range: -2.5239

Max Act: 1.5568. Min Act: -0.0000

Data Index: 550750 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 2.5239. Min Range: -2.5239

Max Act: 1.4163. Min Act: -0.0000

Data Index: 283517 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 2.5239. Min Range: -2.5239

Max Act: 1.4835. Min Act: -0.0000

Data Index: 87640 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 2.5239. Min Range: -2.5239

Max Act: 1.4788. Min Act: -0.0000

Data Index: 354395 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 2.5239. Min Range: -2.5239

Max Act: 1.5442. Min Act: -0.0000

Data Index: 572905 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 2.5239. Min Range: -2.5239

Max Act: 1.4467. Min Act: -0.0000

Data Index: 1355141 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 2.5239. Min Range: -2.5239

Max Act: 1.4786. Min Act: -0.0000

Data Index: 1069657 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 2.5239. Min Range: -2.5239

Max Act: 1.4249. Min Act: -0.0000

Data Index: 1141673 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 2.5239. Min Range: -2.5239

Max Act: 1.3643. Min Act: -0.0000

Data Index: 741054 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 2.5239. Min Range: -2.5239

Max Act: 1.5569. Min Act: -0.0000

Data Index: 1099789 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 2.5239. Min Range: -2.5239

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1019607 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 2.5239. Min Range: -2.5239

Max Act: 1.4081. Min Act: -0.0000

Data Index: 421291 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 2.5239. Min Range: -2.5239

Max Act: 1.3465. Min Act: -0.0000

Data Index: 1140095 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 2.5239. Min Range: -2.5239

Max Act: 1.3908. Min Act: -0.0000

Data Index: 959881 (C4 (Web Text))

Max Activating Token Index: 609