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

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

Neuron 4092 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: 2.4465. Min Range: -2.4465

Max Act: 2.4465. Min Act: -0.0000

Data Index: 17396 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 2.4465. Min Range: -2.4465

Max Act: 2.0104. Min Act: -0.0000

Data Index: 263853 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 2.4465. Min Range: -2.4465

Max Act: 1.9010. Min Act: -0.0000

Data Index: 731419 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 2.4465. Min Range: -2.4465

Max Act: 1.6823. Min Act: -0.0000

Data Index: 656874 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 2.4465. Min Range: -2.4465

Max Act: 1.6533. Min Act: -0.0000

Data Index: 252646 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 2.4465. Min Range: -2.4465

Max Act: 1.4532. Min Act: -0.0000

Data Index: 1190932 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 2.4465. Min Range: -2.4465

Max Act: 1.4739. Min Act: -0.0000

Data Index: 1198264 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 2.4465. Min Range: -2.4465

Max Act: 1.3827. Min Act: -0.0000

Data Index: 931963 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 2.4465. Min Range: -2.4465

Max Act: 1.5375. Min Act: -0.0000

Data Index: 848461 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 2.4465. Min Range: -2.4465

Max Act: 1.4076. Min Act: -0.0000

Data Index: 399380 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 2.4465. Min Range: -2.4465

Max Act: 1.4442. Min Act: -0.0000

Data Index: 1302364 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 2.4465. Min Range: -2.4465

Max Act: 1.3050. Min Act: -0.0000

Data Index: 773171 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 2.4465. Min Range: -2.4465

Max Act: 1.2762. Min Act: -0.0000

Data Index: 661438 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 2.4465. Min Range: -2.4465

Max Act: 1.3447. Min Act: 0.0000

Data Index: 363568 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 2.4465. Min Range: -2.4465

Max Act: 1.3310. Min Act: -0.0000

Data Index: 429382 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 2.4465. Min Range: -2.4465

Max Act: 1.3253. Min Act: -0.0000

Data Index: 701980 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 2.4465. Min Range: -2.4465

Max Act: 1.3632. Min Act: -0.0000

Data Index: 1159428 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 2.4465. Min Range: -2.4465

Max Act: 1.3300. Min Act: -0.0000

Data Index: 1338944 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 2.4465. Min Range: -2.4465

Max Act: 1.3179. Min Act: -0.0000

Data Index: 986197 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 2.4465. Min Range: -2.4465

Max Act: 1.2916. Min Act: -0.0000

Data Index: 754642 (C4 (Web Text))

Max Activating Token Index: 650