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

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

Neuron 4339 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9691. Min Range: -2.9691

Max Act: 2.9691. Min Act: -0.0000

Data Index: 151019 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 2.9691. Min Range: -2.9691

Max Act: 2.7179. Min Act: -0.0000

Data Index: 656332 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 2.9691. Min Range: -2.9691

Max Act: 2.3298. Min Act: -0.0000

Data Index: 808100 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 2.9691. Min Range: -2.9691

Max Act: 2.4544. Min Act: -0.0000

Data Index: 1153122 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 2.9691. Min Range: -2.9691

Max Act: 2.3204. Min Act: -0.0000

Data Index: 626125 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 2.9691. Min Range: -2.9691

Max Act: 2.4125. Min Act: -0.0000

Data Index: 388264 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 2.9691. Min Range: -2.9691

Max Act: 2.3677. Min Act: -0.0000

Data Index: 940992 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 2.9691. Min Range: -2.9691

Max Act: 2.2103. Min Act: -0.0000

Data Index: 615252 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 2.9691. Min Range: -2.9691

Max Act: 2.2109. Min Act: -0.0000

Data Index: 694276 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 2.9691. Min Range: -2.9691

Max Act: 2.2415. Min Act: -0.0000

Data Index: 510885 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 2.9691. Min Range: -2.9691

Max Act: 2.1067. Min Act: -0.0000

Data Index: 784442 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 2.9691. Min Range: -2.9691

Max Act: 2.2259. Min Act: -0.0000

Data Index: 1079119 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 2.9691. Min Range: -2.9691

Max Act: 2.2030. Min Act: -0.0000

Data Index: 293882 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 2.9691. Min Range: -2.9691

Max Act: 2.2800. Min Act: -0.0000

Data Index: 1333046 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 2.9691. Min Range: -2.9691

Max Act: 2.0230. Min Act: -0.0000

Data Index: 75971 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 2.9691. Min Range: -2.9691

Max Act: 2.0714. Min Act: -0.0000

Data Index: 258235 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 2.9691. Min Range: -2.9691

Max Act: 2.1832. Min Act: -0.0000

Data Index: 242298 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 2.9691. Min Range: -2.9691

Max Act: 2.0179. Min Act: -0.0000

Data Index: 1052864 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 2.9691. Min Range: -2.9691

Max Act: 1.8168. Min Act: -0.0000

Data Index: 249213 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 2.9691. Min Range: -2.9691

Max Act: 2.2275. Min Act: -0.0000

Data Index: 695555 (C4 (Web Text))

Max Activating Token Index: 388