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

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

Neuron 2007 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.4083. Min Act: -0.0001

Data Index: 1014025 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.2359. Min Act: -0.0001

Data Index: 1163486 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.0615. Min Act: -0.0001

Data Index: 473454 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.1282. Min Act: -0.0001

Data Index: 611346 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 1.4083. Min Range: -1.4083

Max Act: 0.9850. Min Act: -0.0001

Data Index: 656002 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.0696. Min Act: -0.0001

Data Index: 592074 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 1.4083. Min Range: -1.4083

Max Act: 0.9800. Min Act: -0.0001

Data Index: 727638 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.0073. Min Act: -0.0001

Data Index: 609049 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 1.4083. Min Range: -1.4083

Max Act: 0.9657. Min Act: -0.0001

Data Index: 559468 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 1.4083. Min Range: -1.4083

Max Act: 0.9797. Min Act: -0.0001

Data Index: 824143 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 1.4083. Min Range: -1.4083

Max Act: 0.8963. Min Act: -0.0001

Data Index: 518842 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.0104. Min Act: -0.0001

Data Index: 601021 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 1.4083. Min Range: -1.4083

Max Act: 0.9458. Min Act: -0.0001

Data Index: 1185283 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 1.4083. Min Range: -1.4083

Max Act: 0.9388. Min Act: -0.0001

Data Index: 1098822 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 1.4083. Min Range: -1.4083

Max Act: 0.9014. Min Act: -0.0001

Data Index: 1185517 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 1.4083. Min Range: -1.4083

Max Act: 0.9523. Min Act: -0.0001

Data Index: 1121463 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 1.4083. Min Range: -1.4083

Max Act: 0.8609. Min Act: -0.0001

Data Index: 1180532 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 1.4083. Min Range: -1.4083

Max Act: 0.8574. Min Act: -0.0001

Data Index: 1202133 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 1.4083. Min Range: -1.4083

Max Act: 0.8579. Min Act: -0.0001

Data Index: 647792 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 1.4083. Min Range: -1.4083

Max Act: 0.9101. Min Act: -0.0001

Data Index: 271513 (C4 (Web Text))

Max Activating Token Index: 362