Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1790 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2700. Min Act: -0.0001

Data Index: 1010655 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2266. Min Act: -0.0001

Data Index: 90161 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2246. Min Act: -0.0001

Data Index: 661127 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2154. Min Act: -0.0001

Data Index: 1301891 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2233. Min Act: -0.0001

Data Index: 275598 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2146. Min Act: -0.0001

Data Index: 570083 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2255. Min Act: -0.0001

Data Index: 346720 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2208. Min Act: -0.0001

Data Index: 30656 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2103. Min Act: -0.0001

Data Index: 1339922 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2185. Min Act: -0.0001

Data Index: 615737 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2166. Min Act: -0.0001

Data Index: 134118 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2131. Min Act: -0.0001

Data Index: 101032 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2072. Min Act: -0.0001

Data Index: 640869 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2197. Min Act: -0.0001

Data Index: 1075972 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2205. Min Act: -0.0001

Data Index: 1259713 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2164. Min Act: -0.0001

Data Index: 955262 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2059. Min Act: -0.0001

Data Index: 139849 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2058. Min Act: -0.0001

Data Index: 320424 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2067. Min Act: -0.0001

Data Index: 529457 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2138. Min Act: -0.0001

Data Index: 1282558 (C4 (Web Text))

Max Activating Token Index: 779