Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 254 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.7482. Min Range: -2.7482

Max Act: 2.5866. Min Act: -0.0000

Data Index: 188742 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 2.7482. Min Range: -2.7482

Max Act: 2.5366. Min Act: -0.0000

Data Index: 384854 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 2.7482. Min Range: -2.7482

Max Act: 2.5933. Min Act: -0.0000

Data Index: 936669 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 2.7482. Min Range: -2.7482

Max Act: 2.4851. Min Act: -0.0001

Data Index: 219928 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 2.7482. Min Range: -2.7482

Max Act: 2.6427. Min Act: -0.0000

Data Index: 940821 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 2.7482. Min Range: -2.7482

Max Act: 2.7482. Min Act: -0.0001

Data Index: 772844 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 2.7482. Min Range: -2.7482

Max Act: 2.5513. Min Act: -0.0000

Data Index: 364417 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 2.7482. Min Range: -2.7482

Max Act: 2.5214. Min Act: -0.0001

Data Index: 758053 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 2.7482. Min Range: -2.7482

Max Act: 2.5231. Min Act: -0.0000

Data Index: 681866 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 2.7482. Min Range: -2.7482

Max Act: 2.4641. Min Act: -0.0001

Data Index: 372222 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 2.7482. Min Range: -2.7482

Max Act: 2.6405. Min Act: -0.0001

Data Index: 1194063 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 2.7482. Min Range: -2.7482

Max Act: 2.3853. Min Act: -0.0000

Data Index: 63221 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 2.7482. Min Range: -2.7482

Max Act: 2.3815. Min Act: -0.0000

Data Index: 733242 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 2.7482. Min Range: -2.7482

Max Act: 2.3741. Min Act: -0.0001

Data Index: 437966 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 2.7482. Min Range: -2.7482

Max Act: 2.3691. Min Act: -0.0001

Data Index: 756575 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 2.7482. Min Range: -2.7482

Max Act: 2.4032. Min Act: -0.0000

Data Index: 229781 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 2.7482. Min Range: -2.7482

Max Act: 2.4166. Min Act: -0.0001

Data Index: 1060284 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 2.7482. Min Range: -2.7482

Max Act: 2.5112. Min Act: -0.0001

Data Index: 939434 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 2.7482. Min Range: -2.7482

Max Act: 2.2753. Min Act: -0.0000

Data Index: 450393 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 2.7482. Min Range: -2.7482

Max Act: 2.3445. Min Act: -0.0000

Data Index: 960245 (C4 (Web Text))

Max Activating Token Index: 853