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

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

Neuron 2881 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.6408. Min Act: -0.0004

Data Index: 491950 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.9710. Min Act: -0.0004

Data Index: 339080 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7844. Min Act: -0.0004

Data Index: 1060653 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7149. Min Act: -0.0004

Data Index: 1104845 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.6910. Min Act: -0.0004

Data Index: 133266 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.6248. Min Act: -0.0004

Data Index: 276477 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.5423. Min Act: -0.0004

Data Index: 388345 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.6552. Min Act: -0.0004

Data Index: 1029007 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.6464. Min Act: -0.0004

Data Index: 1268132 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.3327. Min Act: -0.0004

Data Index: 907840 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.6169. Min Act: -0.0004

Data Index: 1021096 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.5551. Min Act: -0.0004

Data Index: 353298 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.6723. Min Act: -0.0004

Data Index: 343846 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.3764. Min Act: -0.0004

Data Index: 451407 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.4888. Min Act: -0.0004

Data Index: 27222 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.3937. Min Act: -0.0004

Data Index: 232307 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.4322. Min Act: -0.0004

Data Index: 1030631 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.6050. Min Act: -0.0004

Data Index: 869154 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.6447. Min Act: -0.0004

Data Index: 876117 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.6648. Min Act: -0.0004

Data Index: 167917 (C4 (Web Text))

Max Activating Token Index: 796