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

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

Neuron 2509 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6778. Min Range: -3.6778

Max Act: 3.6778. Min Act: -0.0001

Data Index: 1320351 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 3.6778. Min Range: -3.6778

Max Act: 3.0545. Min Act: -0.0001

Data Index: 1208391 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 3.6778. Min Range: -3.6778

Max Act: 2.7243. Min Act: -0.0001

Data Index: 416836 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 3.6778. Min Range: -3.6778

Max Act: 3.1337. Min Act: -0.0001

Data Index: 451131 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 3.6778. Min Range: -3.6778

Max Act: 2.9114. Min Act: -0.0001

Data Index: 349545 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 3.6778. Min Range: -3.6778

Max Act: 2.7718. Min Act: -0.0001

Data Index: 309372 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 3.6778. Min Range: -3.6778

Max Act: 2.7419. Min Act: -0.0001

Data Index: 1139882 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 3.6778. Min Range: -3.6778

Max Act: 2.7924. Min Act: -0.0001

Data Index: 46407 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 3.6778. Min Range: -3.6778

Max Act: 2.4500. Min Act: -0.0001

Data Index: 1036748 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 3.6778. Min Range: -3.6778

Max Act: 2.2736. Min Act: -0.0001

Data Index: 302340 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 3.6778. Min Range: -3.6778

Max Act: 2.0592. Min Act: -0.0001

Data Index: 289432 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 3.6778. Min Range: -3.6778

Max Act: 2.3819. Min Act: -0.0001

Data Index: 764279 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 3.6778. Min Range: -3.6778

Max Act: 2.6014. Min Act: -0.0001

Data Index: 1043100 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 3.6778. Min Range: -3.6778

Max Act: 2.5377. Min Act: -0.0001

Data Index: 175117 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 3.6778. Min Range: -3.6778

Max Act: 2.5745. Min Act: -0.0001

Data Index: 1015978 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 3.6778. Min Range: -3.6778

Max Act: 1.9910. Min Act: -0.0001

Data Index: 487922 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 3.6778. Min Range: -3.6778

Max Act: 2.5241. Min Act: -0.0001

Data Index: 249045 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 3.6778. Min Range: -3.6778

Max Act: 2.1784. Min Act: -0.0001

Data Index: 1213864 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 3.6778. Min Range: -3.6778

Max Act: 2.3670. Min Act: -0.0001

Data Index: 991568 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 3.6778. Min Range: -3.6778

Max Act: 2.2214. Min Act: -0.0001

Data Index: 535995 (C4 (Web Text))

Max Activating Token Index: 1011