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

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

Neuron 2920 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0573. Min Range: -1.0573

Max Act: 1.0573. Min Act: -0.0000

Data Index: 942593 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 1.0573. Min Range: -1.0573

Max Act: 1.0368. Min Act: -0.0000

Data Index: 97109 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.8970. Min Act: -0.0000

Data Index: 530870 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.8073. Min Act: -0.0000

Data Index: 358735 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.9023. Min Act: -0.0000

Data Index: 253621 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.8421. Min Act: -0.0000

Data Index: 553907 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.8238. Min Act: -0.0000

Data Index: 757253 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.7531. Min Act: -0.0000

Data Index: 452022 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.7771. Min Act: -0.0000

Data Index: 979917 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.7170. Min Act: -0.0000

Data Index: 870048 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.7207. Min Act: -0.0000

Data Index: 6070 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.6966. Min Act: -0.0000

Data Index: 330518 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.6639. Min Act: -0.0000

Data Index: 582461 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1186593 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.6128. Min Act: -0.0000

Data Index: 675034 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.6277. Min Act: -0.0000

Data Index: 590242 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.6248. Min Act: -0.0000

Data Index: 1277323 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.6227. Min Act: -0.0000

Data Index: 638851 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.6366. Min Act: -0.0000

Data Index: 669035 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.6166. Min Act: 0.0000

Data Index: 1212680 (C4 (Web Text))

Max Activating Token Index: 17