Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1331 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.3628. Min Act: -0.0001

Data Index: 614159 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0818. Min Act: -0.0001

Data Index: 22171 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0423. Min Act: -0.0001

Data Index: 321587 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0021. Min Act: -0.0001

Data Index: 492767 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0394. Min Act: -0.0001

Data Index: 983820 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0001. Min Act: -0.0001

Data Index: 454633 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9736. Min Act: -0.0001

Data Index: 151104 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9763. Min Act: -0.0001

Data Index: 1027831 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9580. Min Act: -0.0001

Data Index: 230888 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9482. Min Act: -0.0001

Data Index: 51954 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9508. Min Act: -0.0001

Data Index: 721883 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9315. Min Act: -0.0001

Data Index: 718408 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9391. Min Act: -0.0001

Data Index: 10878 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9228. Min Act: -0.0001

Data Index: 872381 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9225. Min Act: -0.0001

Data Index: 1291726 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9244. Min Act: -0.0001

Data Index: 726324 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9079. Min Act: -0.0001

Data Index: 539088 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9122. Min Act: -0.0001

Data Index: 222512 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9113. Min Act: -0.0001

Data Index: 347206 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.8924. Min Act: -0.0001

Data Index: 1201568 (C4 (Web Text))

Max Activating Token Index: 145