Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 351 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2384. Min Act: -0.0000

Data Index: 1348417 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2193. Min Act: -0.0000

Data Index: 771318 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1008951 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2113. Min Act: -0.0000

Data Index: 829455 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2217. Min Act: -0.0001

Data Index: 486312 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1775. Min Act: -0.0000

Data Index: 91297 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2119. Min Act: -0.0000

Data Index: 436594 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1971. Min Act: -0.0001

Data Index: 283848 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1828. Min Act: -0.0001

Data Index: 74751 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1915. Min Act: -0.0001

Data Index: 945141 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1921. Min Act: -0.0000

Data Index: 511542 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1969. Min Act: -0.0001

Data Index: 1237833 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1907. Min Act: -0.0000

Data Index: 809156 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1818. Min Act: -0.0001

Data Index: 671873 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1822. Min Act: -0.0000

Data Index: 491120 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1924. Min Act: -0.0000

Data Index: 1186900 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1880. Min Act: -0.0001

Data Index: 920828 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1987. Min Act: -0.0001

Data Index: 1238124 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1849. Min Act: -0.0000

Data Index: 1137651 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1856. Min Act: -0.0001

Data Index: 832897 (C4 (Web Text))

Max Activating Token Index: 613