Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1035 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.3751. Min Act: -0.0001

Data Index: 206415 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4438. Min Act: -0.0001

Data Index: 1049079 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.5484. Min Act: -0.0001

Data Index: 9237 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.5680. Min Act: -0.0001

Data Index: 929002 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4155. Min Act: -0.0001

Data Index: 914167 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4096. Min Act: -0.0001

Data Index: 1133395 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4812. Min Act: -0.0001

Data Index: 62296 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.5110. Min Act: -0.0001

Data Index: 475831 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4801. Min Act: -0.0001

Data Index: 176718 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.5778. Min Act: -0.0001

Data Index: 343350 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.6303. Min Act: -0.0001

Data Index: 223864 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.6159. Min Act: -0.0001

Data Index: 1275955 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4783. Min Act: -0.0001

Data Index: 610580 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4477. Min Act: -0.0001

Data Index: 270460 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4982. Min Act: -0.0001

Data Index: 288580 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.3282. Min Act: -0.0001

Data Index: 1085531 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4197. Min Act: -0.0001

Data Index: 481796 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4436. Min Act: -0.0001

Data Index: 166713 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.3815. Min Act: -0.0001

Data Index: 784721 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.3697. Min Act: -0.0001

Data Index: 491796 (C4 (Web Text))

Max Activating Token Index: 103