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

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

Neuron 1977 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9886. Min Range: -3.9886

Max Act: 3.9782. Min Act: -0.0000

Data Index: 425009 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 3.9886. Min Range: -3.9886

Max Act: 3.4569. Min Act: -0.0000

Data Index: 335496 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 3.9886. Min Range: -3.9886

Max Act: 3.8057. Min Act: -0.0000

Data Index: 642654 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 3.9886. Min Range: -3.9886

Max Act: 3.8536. Min Act: -0.0000

Data Index: 127493 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 3.9886. Min Range: -3.9886

Max Act: 3.8726. Min Act: -0.0000

Data Index: 1303964 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 3.9886. Min Range: -3.9886

Max Act: 3.9886. Min Act: -0.0000

Data Index: 49845 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 3.9886. Min Range: -3.9886

Max Act: 3.5919. Min Act: -0.0000

Data Index: 1142473 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 3.9886. Min Range: -3.9886

Max Act: 3.4161. Min Act: -0.0000

Data Index: 2546 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 3.9886. Min Range: -3.9886

Max Act: 3.3730. Min Act: -0.0000

Data Index: 342162 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 3.9886. Min Range: -3.9886

Max Act: 3.6850. Min Act: -0.0000

Data Index: 146346 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 3.9886. Min Range: -3.9886

Max Act: 3.4847. Min Act: -0.0000

Data Index: 899871 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 3.9886. Min Range: -3.9886

Max Act: 3.3632. Min Act: -0.0000

Data Index: 703115 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 3.9886. Min Range: -3.9886

Max Act: 3.4875. Min Act: -0.0000

Data Index: 162179 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 3.9886. Min Range: -3.9886

Max Act: 3.4647. Min Act: -0.0000

Data Index: 501885 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 3.9886. Min Range: -3.9886

Max Act: 3.3078. Min Act: -0.0000

Data Index: 1009230 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 3.9886. Min Range: -3.9886

Max Act: 3.3137. Min Act: -0.0000

Data Index: 663023 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 3.9886. Min Range: -3.9886

Max Act: 3.4795. Min Act: -0.0000

Data Index: 379155 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 3.9886. Min Range: -3.9886

Max Act: 3.4274. Min Act: -0.0000

Data Index: 769487 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 3.9886. Min Range: -3.9886

Max Act: 3.1425. Min Act: -0.0000

Data Index: 115318 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 3.9886. Min Range: -3.9886

Max Act: 3.2923. Min Act: -0.0000

Data Index: 739755 (C4 (Web Text))

Max Activating Token Index: 97