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

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

Neuron 602 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: 3.7444. Min Range: -3.7444

Max Act: 3.7444. Min Act: -0.0001

Data Index: 955883 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 3.7444. Min Range: -3.7444

Max Act: 3.5067. Min Act: -0.0001

Data Index: 103254 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 3.7444. Min Range: -3.7444

Max Act: 3.5143. Min Act: -0.0001

Data Index: 788559 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 3.7444. Min Range: -3.7444

Max Act: 3.5335. Min Act: -0.0001

Data Index: 562268 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 3.7444. Min Range: -3.7444

Max Act: 3.5166. Min Act: -0.0001

Data Index: 932188 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 3.7444. Min Range: -3.7444

Max Act: 3.3926. Min Act: -0.0001

Data Index: 1175434 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 3.7444. Min Range: -3.7444

Max Act: 3.5094. Min Act: -0.0001

Data Index: 979895 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 3.7444. Min Range: -3.7444

Max Act: 3.2854. Min Act: -0.0001

Data Index: 824168 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 3.7444. Min Range: -3.7444

Max Act: 3.0834. Min Act: -0.0001

Data Index: 527780 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 3.7444. Min Range: -3.7444

Max Act: 3.1756. Min Act: -0.0001

Data Index: 598181 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 3.7444. Min Range: -3.7444

Max Act: 2.7500. Min Act: -0.0001

Data Index: 553957 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 3.7444. Min Range: -3.7444

Max Act: 2.8985. Min Act: -0.0001

Data Index: 393368 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 3.7444. Min Range: -3.7444

Max Act: 2.6664. Min Act: -0.0001

Data Index: 266803 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 3.7444. Min Range: -3.7444

Max Act: 2.7707. Min Act: -0.0001

Data Index: 690956 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 3.7444. Min Range: -3.7444

Max Act: 2.5622. Min Act: -0.0001

Data Index: 70444 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 3.7444. Min Range: -3.7444

Max Act: 2.5909. Min Act: -0.0001

Data Index: 377935 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 3.7444. Min Range: -3.7444

Max Act: 2.4564. Min Act: -0.0001

Data Index: 424786 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 3.7444. Min Range: -3.7444

Max Act: 2.4543. Min Act: -0.0001

Data Index: 147827 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 3.7444. Min Range: -3.7444

Max Act: 2.4262. Min Act: -0.0001

Data Index: 827780 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 3.7444. Min Range: -3.7444

Max Act: 2.9065. Min Act: -0.0001

Data Index: 98277 (C4 (Web Text))

Max Activating Token Index: 290