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

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

Neuron 3204 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.6708. Min Act: -0.0000

Data Index: 65055 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.5522. Min Act: -0.0000

Data Index: 887973 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.5364. Min Act: -0.0000

Data Index: 873439 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1146804 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.5612. Min Act: -0.0000

Data Index: 450727 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4832. Min Act: -0.0000

Data Index: 822236 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4649. Min Act: -0.0000

Data Index: 947953 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4339. Min Act: -0.0000

Data Index: 268599 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4173. Min Act: -0.0000

Data Index: 1069064 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4296. Min Act: -0.0000

Data Index: 1133118 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4223. Min Act: 0.0000

Data Index: 989821 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4213. Min Act: -0.0000

Data Index: 1135267 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4137. Min Act: -0.0000

Data Index: 962168 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4251. Min Act: -0.0000

Data Index: 336389 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1237947 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.3948. Min Act: -0.0000

Data Index: 637166 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4154. Min Act: -0.0000

Data Index: 483104 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.3747. Min Act: -0.0000

Data Index: 155346 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.4212. Min Act: -0.0000

Data Index: 642743 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.3833. Min Act: -0.0000

Data Index: 4588 (C4 (Web Text))

Max Activating Token Index: 58