Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3642 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2089. Min Range: -2.2089

Max Act: 2.2089. Min Act: -0.0000

Data Index: 575457 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 2.2089. Min Range: -2.2089

Max Act: 1.9691. Min Act: -0.0000

Data Index: 761428 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 2.2089. Min Range: -2.2089

Max Act: 2.0467. Min Act: -0.0000

Data Index: 39505 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 2.2089. Min Range: -2.2089

Max Act: 1.8452. Min Act: -0.0000

Data Index: 303984 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 2.2089. Min Range: -2.2089

Max Act: 2.0253. Min Act: -0.0000

Data Index: 607786 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 2.2089. Min Range: -2.2089

Max Act: 2.0225. Min Act: -0.0000

Data Index: 79946 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 2.2089. Min Range: -2.2089

Max Act: 1.8901. Min Act: -0.0000

Data Index: 406920 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 2.2089. Min Range: -2.2089

Max Act: 1.6531. Min Act: -0.0000

Data Index: 882095 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 2.2089. Min Range: -2.2089

Max Act: 1.8363. Min Act: -0.0000

Data Index: 1006086 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 2.2089. Min Range: -2.2089

Max Act: 1.8185. Min Act: -0.0000

Data Index: 991858 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 2.2089. Min Range: -2.2089

Max Act: 1.8981. Min Act: -0.0000

Data Index: 517957 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 2.2089. Min Range: -2.2089

Max Act: 1.6898. Min Act: -0.0000

Data Index: 1310037 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 2.2089. Min Range: -2.2089

Max Act: 1.6646. Min Act: -0.0000

Data Index: 1081519 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 2.2089. Min Range: -2.2089

Max Act: 1.7002. Min Act: -0.0000

Data Index: 419966 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 2.2089. Min Range: -2.2089

Max Act: 1.7571. Min Act: -0.0000

Data Index: 656821 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 2.2089. Min Range: -2.2089

Max Act: 1.7575. Min Act: -0.0000

Data Index: 953988 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 2.2089. Min Range: -2.2089

Max Act: 1.7792. Min Act: -0.0000

Data Index: 449017 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 2.2089. Min Range: -2.2089

Max Act: 1.7249. Min Act: -0.0000

Data Index: 586290 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 2.2089. Min Range: -2.2089

Max Act: 1.7126. Min Act: -0.0000

Data Index: 610061 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 2.2089. Min Range: -2.2089

Max Act: 1.6579. Min Act: -0.0000

Data Index: 79337 (C4 (Web Text))

Max Activating Token Index: 211