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

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

Neuron 3726 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.5680. Min Act: -0.0001

Data Index: 711929 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.5136. Min Act: -0.0001

Data Index: 1272393 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4829. Min Act: -0.0001

Data Index: 1052036 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4915. Min Act: -0.0001

Data Index: 1166391 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.5040. Min Act: -0.0001

Data Index: 590819 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4832. Min Act: -0.0001

Data Index: 1027786 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4644. Min Act: -0.0001

Data Index: 422199 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4410. Min Act: -0.0001

Data Index: 903892 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4431. Min Act: -0.0001

Data Index: 901803 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4541. Min Act: -0.0001

Data Index: 618029 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4137. Min Act: -0.0001

Data Index: 1125619 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4568. Min Act: -0.0001

Data Index: 311461 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4393. Min Act: -0.0001

Data Index: 1355841 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4320. Min Act: -0.0001

Data Index: 666163 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4387. Min Act: -0.0001

Data Index: 798821 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4224. Min Act: -0.0001

Data Index: 122759 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4339. Min Act: -0.0001

Data Index: 244641 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4322. Min Act: -0.0001

Data Index: 1271299 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4355. Min Act: -0.0001

Data Index: 409182 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4411. Min Act: -0.0001

Data Index: 785888 (C4 (Web Text))

Max Activating Token Index: 352