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

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

Neuron 1004 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0089. Min Act: -0.0003

Data Index: 1156971 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0080. Min Act: -0.0003

Data Index: 610434 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0074. Min Act: -0.0004

Data Index: 1112113 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0072. Min Act: -0.0003

Data Index: 306298 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0071. Min Act: -0.0004

Data Index: 1082810 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0072. Min Act: -0.0003

Data Index: 785995 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0071. Min Act: -0.0003

Data Index: 564641 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0071. Min Act: -0.0003

Data Index: 1042171 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1312436 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0067. Min Act: -0.0004

Data Index: 801886 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0067. Min Act: -0.0003

Data Index: 235832 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0066. Min Act: -0.0004

Data Index: 101064 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0065. Min Act: -0.0004

Data Index: 97356 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0065. Min Act: -0.0004

Data Index: 556907 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0065. Min Act: -0.0004

Data Index: 560159 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0066. Min Act: -0.0003

Data Index: 528603 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0065. Min Act: -0.0003

Data Index: 592765 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0066. Min Act: -0.0004

Data Index: 550779 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0065. Min Act: -0.0003

Data Index: 990976 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0065. Min Act: -0.0003

Data Index: 403312 (C4 (Web Text))

Max Activating Token Index: 995