Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4435 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1521. Min Range: -2.1521

Max Act: 2.1521. Min Act: -0.0000

Data Index: 684114 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 2.1521. Min Range: -2.1521

Max Act: 1.7913. Min Act: -0.0000

Data Index: 119145 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 2.1521. Min Range: -2.1521

Max Act: 1.6951. Min Act: -0.0000

Data Index: 757468 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 2.1521. Min Range: -2.1521

Max Act: 1.8895. Min Act: -0.0000

Data Index: 613804 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 2.1521. Min Range: -2.1521

Max Act: 1.6572. Min Act: -0.0000

Data Index: 886081 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 2.1521. Min Range: -2.1521

Max Act: 1.6709. Min Act: -0.0000

Data Index: 396726 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 2.1521. Min Range: -2.1521

Max Act: 1.6583. Min Act: -0.0000

Data Index: 362863 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 2.1521. Min Range: -2.1521

Max Act: 1.7625. Min Act: -0.0000

Data Index: 942790 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 2.1521. Min Range: -2.1521

Max Act: 1.8262. Min Act: -0.0000

Data Index: 604034 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 2.1521. Min Range: -2.1521

Max Act: 1.5782. Min Act: -0.0000

Data Index: 923206 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 2.1521. Min Range: -2.1521

Max Act: 1.5815. Min Act: -0.0000

Data Index: 271375 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 2.1521. Min Range: -2.1521

Max Act: 1.4775. Min Act: -0.0000

Data Index: 851963 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 2.1521. Min Range: -2.1521

Max Act: 1.5440. Min Act: -0.0000

Data Index: 206384 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 2.1521. Min Range: -2.1521

Max Act: 1.4074. Min Act: -0.0000

Data Index: 1123921 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 2.1521. Min Range: -2.1521

Max Act: 1.4814. Min Act: -0.0000

Data Index: 103459 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 2.1521. Min Range: -2.1521

Max Act: 1.4520. Min Act: -0.0000

Data Index: 226454 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 2.1521. Min Range: -2.1521

Max Act: 1.4150. Min Act: -0.0000

Data Index: 367212 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 2.1521. Min Range: -2.1521

Max Act: 1.4163. Min Act: -0.0000

Data Index: 526622 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 2.1521. Min Range: -2.1521

Max Act: 1.4119. Min Act: -0.0000

Data Index: 810301 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 2.1521. Min Range: -2.1521

Max Act: 1.3097. Min Act: -0.0000

Data Index: 734712 (C4 (Web Text))

Max Activating Token Index: 944