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

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

Neuron 1448 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8538. Min Range: -1.8538

Max Act: 1.8538. Min Act: -0.0001

Data Index: 225495 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 1.8538. Min Range: -1.8538

Max Act: 1.7567. Min Act: -0.0001

Data Index: 910125 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 1.8538. Min Range: -1.8538

Max Act: 1.5784. Min Act: -0.0001

Data Index: 1051466 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 1.8538. Min Range: -1.8538

Max Act: 1.7458. Min Act: -0.0001

Data Index: 1344116 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 1.8538. Min Range: -1.8538

Max Act: 1.7034. Min Act: -0.0001

Data Index: 53864 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 1.8538. Min Range: -1.8538

Max Act: 1.6053. Min Act: -0.0001

Data Index: 980895 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 1.8538. Min Range: -1.8538

Max Act: 1.6031. Min Act: -0.0000

Data Index: 462345 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 1.8538. Min Range: -1.8538

Max Act: 1.4886. Min Act: -0.0001

Data Index: 421478 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 1.8538. Min Range: -1.8538

Max Act: 1.4598. Min Act: -0.0001

Data Index: 997140 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 1.8538. Min Range: -1.8538

Max Act: 1.5522. Min Act: -0.0001

Data Index: 1083153 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 1.8538. Min Range: -1.8538

Max Act: 1.6284. Min Act: -0.0001

Data Index: 862820 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 1.8538. Min Range: -1.8538

Max Act: 1.4395. Min Act: -0.0000

Data Index: 502351 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 1.8538. Min Range: -1.8538

Max Act: 1.4736. Min Act: -0.0001

Data Index: 1165680 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 1.8538. Min Range: -1.8538

Max Act: 1.5234. Min Act: -0.0001

Data Index: 1277681 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 1.8538. Min Range: -1.8538

Max Act: 1.4591. Min Act: -0.0001

Data Index: 557676 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 1.8538. Min Range: -1.8538

Max Act: 1.5674. Min Act: -0.0001

Data Index: 1228732 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 1.8538. Min Range: -1.8538

Max Act: 1.4018. Min Act: -0.0001

Data Index: 26858 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 1.8538. Min Range: -1.8538

Max Act: 1.5689. Min Act: -0.0001

Data Index: 1199454 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 1.8538. Min Range: -1.8538

Max Act: 1.4100. Min Act: -0.0001

Data Index: 575058 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 1.8538. Min Range: -1.8538

Max Act: 1.3871. Min Act: -0.0000

Data Index: 522382 (C4 (Web Text))

Max Activating Token Index: 18