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

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

Neuron 4057 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: 0.6344. Min Range: -0.6344

Max Act: 0.6344. Min Act: -0.0001

Data Index: 611593 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5689. Min Act: -0.0001

Data Index: 953957 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.4842. Min Act: -0.0001

Data Index: 312071 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.4555. Min Act: -0.0001

Data Index: 1133877 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.4624. Min Act: -0.0001

Data Index: 747791 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.4019. Min Act: -0.0001

Data Index: 668019 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.3856. Min Act: -0.0001

Data Index: 297493 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.4109. Min Act: -0.0001

Data Index: 756143 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.4345. Min Act: -0.0001

Data Index: 224881 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.4334. Min Act: -0.0001

Data Index: 588944 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.4231. Min Act: -0.0001

Data Index: 1078144 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.3926. Min Act: -0.0001

Data Index: 1030690 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.4091. Min Act: -0.0001

Data Index: 720723 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.3444. Min Act: -0.0001

Data Index: 1277001 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.3998. Min Act: -0.0001

Data Index: 344771 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.3810. Min Act: -0.0001

Data Index: 46343 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.3859. Min Act: -0.0001

Data Index: 939872 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.3800. Min Act: -0.0001

Data Index: 336377 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.3838. Min Act: -0.0001

Data Index: 585620 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.3698. Min Act: -0.0001

Data Index: 1075800 (C4 (Web Text))

Max Activating Token Index: 280