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

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

Neuron 3385 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.3157. Min Act: -0.0000

Data Index: 1023574 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2499. Min Act: -0.0000

Data Index: 1130263 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2461. Min Act: 0.0000

Data Index: 106702 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2470. Min Act: -0.0000

Data Index: 512913 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2512. Min Act: -0.0000

Data Index: 245382 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2401. Min Act: -0.0000

Data Index: 99131 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2267. Min Act: -0.0000

Data Index: 481747 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1145912 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2251. Min Act: -0.0000

Data Index: 395308 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1316898 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2304. Min Act: -0.0000

Data Index: 1309286 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2202. Min Act: -0.0000

Data Index: 179557 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2218. Min Act: -0.0000

Data Index: 848680 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2143. Min Act: -0.0000

Data Index: 361136 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2265. Min Act: -0.0000

Data Index: 7708 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2121. Min Act: -0.0000

Data Index: 787475 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2076. Min Act: -0.0000

Data Index: 1340874 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2144. Min Act: -0.0000

Data Index: 817586 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2135. Min Act: -0.0000

Data Index: 213681 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2119. Min Act: -0.0000

Data Index: 160739 (C4 (Web Text))

Max Activating Token Index: 365