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

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

Neuron 822 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: 0.5526. Min Range: -0.5526

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1266963 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4962. Min Act: -0.0000

Data Index: 244555 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1274003 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1219508 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4679. Min Act: -0.0000

Data Index: 886814 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4442. Min Act: -0.0000

Data Index: 541206 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4575. Min Act: -0.0000

Data Index: 891018 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4466. Min Act: -0.0000

Data Index: 704085 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4267. Min Act: -0.0000

Data Index: 2738 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4267. Min Act: -0.0000

Data Index: 846460 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4529. Min Act: -0.0000

Data Index: 404835 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4207. Min Act: -0.0000

Data Index: 1160946 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.3983. Min Act: -0.0000

Data Index: 4430 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4157. Min Act: -0.0000

Data Index: 162200 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4317. Min Act: -0.0000

Data Index: 424163 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4131. Min Act: -0.0000

Data Index: 796261 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4070. Min Act: -0.0000

Data Index: 904479 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.3746. Min Act: -0.0000

Data Index: 746090 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.3963. Min Act: -0.0000

Data Index: 529802 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.3919. Min Act: -0.0000

Data Index: 1154013 (C4 (Web Text))

Max Activating Token Index: 840