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

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

Neuron 4726 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0255. Min Range: -1.0255

Max Act: 1.0135. Min Act: -0.0000

Data Index: 370328 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 1.0255. Min Range: -1.0255

Max Act: 1.0255. Min Act: -0.0000

Data Index: 778374 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 1.0255. Min Range: -1.0255

Max Act: 0.9595. Min Act: -0.0000

Data Index: 1046275 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 1.0255. Min Range: -1.0255

Max Act: 0.9090. Min Act: -0.0000

Data Index: 135376 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 1.0255. Min Range: -1.0255

Max Act: 0.9022. Min Act: -0.0000

Data Index: 504990 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 1.0255. Min Range: -1.0255

Max Act: 0.8973. Min Act: -0.0000

Data Index: 676439 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 1.0255. Min Range: -1.0255

Max Act: 0.8343. Min Act: 0.0001

Data Index: 798040 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 1.0255. Min Range: -1.0255

Max Act: 0.7778. Min Act: -0.0000

Data Index: 276789 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 1.0255. Min Range: -1.0255

Max Act: 0.7377. Min Act: -0.0000

Data Index: 662341 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 1.0255. Min Range: -1.0255

Max Act: 0.7556. Min Act: -0.0000

Data Index: 505408 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 1.0255. Min Range: -1.0255

Max Act: 0.7845. Min Act: -0.0000

Data Index: 714775 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 1.0255. Min Range: -1.0255

Max Act: 0.7399. Min Act: -0.0000

Data Index: 1232853 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 1.0255. Min Range: -1.0255

Max Act: 0.7029. Min Act: 0.0000

Data Index: 592483 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 1.0255. Min Range: -1.0255

Max Act: 0.7062. Min Act: -0.0000

Data Index: 1139682 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 1.0255. Min Range: -1.0255

Max Act: 0.7208. Min Act: -0.0000

Data Index: 1622078 (Python Code)

Max Activating Token Index: 965

Text #15

Max Range: 1.0255. Min Range: -1.0255

Max Act: 0.7200. Min Act: -0.0000

Data Index: 530336 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 1.0255. Min Range: -1.0255

Max Act: 0.7012. Min Act: 0.0001

Data Index: 334550 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 1.0255. Min Range: -1.0255

Max Act: 0.7137. Min Act: -0.0000

Data Index: 1155945 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 1.0255. Min Range: -1.0255

Max Act: 0.6879. Min Act: 0.0000

Data Index: 429062 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 1.0255. Min Range: -1.0255

Max Act: 0.7081. Min Act: 0.0000

Data Index: 771630 (C4 (Web Text))

Max Activating Token Index: 84