Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2809 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3907. Min Range: -1.3907

Max Act: 1.3907. Min Act: -0.0001

Data Index: 629500 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 1.3907. Min Range: -1.3907

Max Act: 1.3302. Min Act: -0.0001

Data Index: 590412 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 1.3907. Min Range: -1.3907

Max Act: 1.0811. Min Act: -0.0001

Data Index: 255804 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 1.3907. Min Range: -1.3907

Max Act: 1.0345. Min Act: -0.0001

Data Index: 311032 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 1.3907. Min Range: -1.3907

Max Act: 1.0543. Min Act: -0.0001

Data Index: 658080 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 1.3907. Min Range: -1.3907

Max Act: 1.0265. Min Act: -0.0001

Data Index: 389546 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 1.3907. Min Range: -1.3907

Max Act: 1.0067. Min Act: -0.0001

Data Index: 1349270 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 1.3907. Min Range: -1.3907

Max Act: 0.9517. Min Act: -0.0001

Data Index: 710785 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 1.3907. Min Range: -1.3907

Max Act: 0.9043. Min Act: -0.0001

Data Index: 43099 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 1.3907. Min Range: -1.3907

Max Act: 0.9100. Min Act: -0.0001

Data Index: 104524 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 1.3907. Min Range: -1.3907

Max Act: 0.9152. Min Act: -0.0001

Data Index: 1301130 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 1.3907. Min Range: -1.3907

Max Act: 0.9304. Min Act: -0.0001

Data Index: 595603 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 1.3907. Min Range: -1.3907

Max Act: 1.0317. Min Act: -0.0001

Data Index: 554923 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 1.3907. Min Range: -1.3907

Max Act: 0.9058. Min Act: -0.0001

Data Index: 53453 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 1.3907. Min Range: -1.3907

Max Act: 0.9722. Min Act: -0.0001

Data Index: 52222 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 1.3907. Min Range: -1.3907

Max Act: 0.8856. Min Act: -0.0001

Data Index: 405381 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 1.3907. Min Range: -1.3907

Max Act: 0.8974. Min Act: -0.0001

Data Index: 131362 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 1.3907. Min Range: -1.3907

Max Act: 0.8076. Min Act: -0.0001

Data Index: 1304787 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 1.3907. Min Range: -1.3907

Max Act: 0.8744. Min Act: -0.0001

Data Index: 700402 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 1.3907. Min Range: -1.3907

Max Act: 0.8472. Min Act: -0.0001

Data Index: 1327081 (C4 (Web Text))

Max Activating Token Index: 293