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

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

Neuron 156 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3062. Min Range: -0.3062

Max Act: 0.3062. Min Act: -0.0000

Data Index: 152779 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.3062. Min Range: -0.3062

Max Act: 0.2987. Min Act: -0.0000

Data Index: 1214870 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 0.3062. Min Range: -0.3062

Max Act: 0.2505. Min Act: -0.0000

Data Index: 1285654 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.3062. Min Range: -0.3062

Max Act: 0.2453. Min Act: -0.0000

Data Index: 736216 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.3062. Min Range: -0.3062

Max Act: 0.2532. Min Act: -0.0000

Data Index: 1356952 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.3062. Min Range: -0.3062

Max Act: 0.2419. Min Act: -0.0000

Data Index: 916095 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.3062. Min Range: -0.3062

Max Act: 0.2311. Min Act: -0.0000

Data Index: 1198027 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.3062. Min Range: -0.3062

Max Act: 0.2228. Min Act: -0.0000

Data Index: 788672 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.3062. Min Range: -0.3062

Max Act: 0.1856. Min Act: -0.0000

Data Index: 995152 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.3062. Min Range: -0.3062

Max Act: 0.1921. Min Act: -0.0000

Data Index: 983689 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.3062. Min Range: -0.3062

Max Act: 0.1696. Min Act: -0.0000

Data Index: 668561 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.3062. Min Range: -0.3062

Max Act: 0.1599. Min Act: -0.0000

Data Index: 62767 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.3062. Min Range: -0.3062

Max Act: 0.1807. Min Act: -0.0000

Data Index: 51277 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 0.3062. Min Range: -0.3062

Max Act: 0.1758. Min Act: -0.0000

Data Index: 1231145 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.3062. Min Range: -0.3062

Max Act: 0.1597. Min Act: -0.0000

Data Index: 1117601 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 0.3062. Min Range: -0.3062

Max Act: 0.1559. Min Act: -0.0000

Data Index: 770319 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.3062. Min Range: -0.3062

Max Act: 0.1614. Min Act: -0.0000

Data Index: 1306362 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 0.3062. Min Range: -0.3062

Max Act: 0.1550. Min Act: -0.0000

Data Index: 912163 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.3062. Min Range: -0.3062

Max Act: 0.1513. Min Act: -0.0000

Data Index: 491956 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.3062. Min Range: -0.3062

Max Act: 0.1540. Min Act: -0.0000

Data Index: 840328 (C4 (Web Text))

Max Activating Token Index: 419