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

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

Neuron 1788 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: 0.8074. Min Range: -0.8074

Max Act: 0.8074. Min Act: -0.0000

Data Index: 785010 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.7432. Min Act: -0.0000

Data Index: 521173 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6556. Min Act: -0.0000

Data Index: 225863 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6399. Min Act: -0.0000

Data Index: 918220 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5955. Min Act: -0.0000

Data Index: 1206284 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5828. Min Act: -0.0000

Data Index: 595196 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6058. Min Act: -0.0000

Data Index: 564432 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5776. Min Act: -0.0000

Data Index: 879102 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5672. Min Act: -0.0000

Data Index: 1045207 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5650. Min Act: -0.0000

Data Index: 1055341 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5346. Min Act: -0.0000

Data Index: 1102103 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5147. Min Act: -0.0000

Data Index: 1057808 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5494. Min Act: -0.0000

Data Index: 608362 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1265677 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5377. Min Act: -0.0000

Data Index: 401207 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5043. Min Act: -0.0000

Data Index: 627529 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1389273 (Python Code)

Max Activating Token Index: 720

Text #17

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5289. Min Act: -0.0000

Data Index: 982461 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1160314 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5035. Min Act: -0.0000

Data Index: 1140424 (C4 (Web Text))

Max Activating Token Index: 433