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

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

Neuron 1552 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.4701. Min Act: -0.0000

Data Index: 981914 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.4278. Min Act: -0.0000

Data Index: 949396 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2861. Min Act: -0.0000

Data Index: 628354 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3176. Min Act: -0.0000

Data Index: 1144121 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3105. Min Act: -0.0000

Data Index: 333784 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3064. Min Act: -0.0000

Data Index: 23393 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2908. Min Act: -0.0000

Data Index: 1215448 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3091. Min Act: -0.0000

Data Index: 1144336 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2437. Min Act: -0.0000

Data Index: 1004651 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2277. Min Act: -0.0000

Data Index: 778367 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2334. Min Act: -0.0000

Data Index: 438209 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2064. Min Act: -0.0000

Data Index: 918780 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2053. Min Act: -0.0000

Data Index: 878662 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1295122 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.1932. Min Act: -0.0000

Data Index: 1282799 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.1902. Min Act: -0.0000

Data Index: 708299 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.1633. Min Act: -0.0000

Data Index: 960705 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.1750. Min Act: -0.0000

Data Index: 1496485 (Python Code)

Max Activating Token Index: 165

Text #18

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.1727. Min Act: -0.0000

Data Index: 330746 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.1684. Min Act: -0.0000

Data Index: 1186789 (C4 (Web Text))

Max Activating Token Index: 826