Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5025 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.7573. Min Act: -0.0000

Data Index: 215340 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.9028. Min Act: -0.0000

Data Index: 96312 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.8449. Min Act: -0.0000

Data Index: 1036694 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.8324. Min Act: -0.0000

Data Index: 500820 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.3596. Min Act: -0.0000

Data Index: 768283 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.5137. Min Act: -0.0000

Data Index: 698089 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.1738. Min Act: -0.0000

Data Index: 611481 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.3019. Min Act: -0.0000

Data Index: 438590 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.5489. Min Act: -0.0000

Data Index: 1072379 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.0435. Min Act: -0.0000

Data Index: 528654 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.1464. Min Act: -0.0000

Data Index: 409429 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.4632. Min Act: -0.0000

Data Index: 297982 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.1904. Min Act: -0.0000

Data Index: 1325851 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.1648. Min Act: -0.0000

Data Index: 889949 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 3.9028. Min Range: -3.9028

Max Act: 2.9155. Min Act: -0.0000

Data Index: 1058906 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 3.9028. Min Range: -3.9028

Max Act: 2.9771. Min Act: -0.0000

Data Index: 47986 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.2828. Min Act: -0.0000

Data Index: 230975 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 3.9028. Min Range: -3.9028

Max Act: 2.9747. Min Act: -0.0000

Data Index: 1034381 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.1022. Min Act: -0.0000

Data Index: 1300869 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.1146. Min Act: -0.0000

Data Index: 918536 (C4 (Web Text))

Max Activating Token Index: 133