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

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

Neuron 1463 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2458. Min Act: -0.0001

Data Index: 323307 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2401. Min Act: -0.0001

Data Index: 164486 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2298. Min Act: -0.0001

Data Index: 1135547 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2311. Min Act: -0.0001

Data Index: 1030747 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2303. Min Act: -0.0001

Data Index: 262358 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2229. Min Act: -0.0001

Data Index: 1237707 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2209. Min Act: -0.0001

Data Index: 937937 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2142. Min Act: -0.0001

Data Index: 507216 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2128. Min Act: -0.0001

Data Index: 61858 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2131. Min Act: -0.0001

Data Index: 628071 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2189. Min Act: -0.0001

Data Index: 882147 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2091. Min Act: -0.0001

Data Index: 1257543 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2076. Min Act: -0.0001

Data Index: 1279737 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2120. Min Act: -0.0001

Data Index: 992338 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2032. Min Act: -0.0001

Data Index: 546709 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1944. Min Act: -0.0001

Data Index: 992905 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2003. Min Act: -0.0001

Data Index: 125307 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1189162 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1984. Min Act: -0.0001

Data Index: 1186932 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1970. Min Act: -0.0001

Data Index: 256797 (C4 (Web Text))

Max Activating Token Index: 996