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

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

Neuron 4768 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9643. Min Range: -5.9643

Max Act: 5.9643. Min Act: -0.0000

Data Index: 1018212 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 5.9643. Min Range: -5.9643

Max Act: 4.8253. Min Act: -0.0000

Data Index: 1287586 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 5.9643. Min Range: -5.9643

Max Act: 4.5747. Min Act: -0.0000

Data Index: 831126 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 5.9643. Min Range: -5.9643

Max Act: 4.5311. Min Act: -0.0000

Data Index: 924178 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 5.9643. Min Range: -5.9643

Max Act: 4.4810. Min Act: -0.0000

Data Index: 1000368 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 5.9643. Min Range: -5.9643

Max Act: 4.5735. Min Act: -0.0000

Data Index: 84748 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 5.9643. Min Range: -5.9643

Max Act: 3.9472. Min Act: -0.0000

Data Index: 573757 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 5.9643. Min Range: -5.9643

Max Act: 4.3079. Min Act: -0.0000

Data Index: 169882 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 5.9643. Min Range: -5.9643

Max Act: 4.2686. Min Act: -0.0000

Data Index: 296900 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 5.9643. Min Range: -5.9643

Max Act: 4.2594. Min Act: -0.0000

Data Index: 581267 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 5.9643. Min Range: -5.9643

Max Act: 4.1086. Min Act: -0.0000

Data Index: 712449 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 5.9643. Min Range: -5.9643

Max Act: 4.2771. Min Act: -0.0000

Data Index: 956235 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 5.9643. Min Range: -5.9643

Max Act: 4.2258. Min Act: -0.0000

Data Index: 777194 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 5.9643. Min Range: -5.9643

Max Act: 4.0425. Min Act: -0.0000

Data Index: 922034 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 5.9643. Min Range: -5.9643

Max Act: 3.8376. Min Act: -0.0000

Data Index: 567683 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 5.9643. Min Range: -5.9643

Max Act: 4.0265. Min Act: -0.0000

Data Index: 609416 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 5.9643. Min Range: -5.9643

Max Act: 4.1558. Min Act: -0.0000

Data Index: 854684 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 5.9643. Min Range: -5.9643

Max Act: 3.9700. Min Act: -0.0000

Data Index: 455949 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 5.9643. Min Range: -5.9643

Max Act: 3.9680. Min Act: -0.0000

Data Index: 187095 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 5.9643. Min Range: -5.9643

Max Act: 3.9704. Min Act: -0.0000

Data Index: 1078847 (C4 (Web Text))

Max Activating Token Index: 747