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

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

Neuron 1223 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3643. Min Range: -2.3643

Max Act: 2.3643. Min Act: -0.0000

Data Index: 415620 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 2.3643. Min Range: -2.3643

Max Act: 2.0337. Min Act: -0.0000

Data Index: 642544 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 2.3643. Min Range: -2.3643

Max Act: 2.2077. Min Act: -0.0000

Data Index: 370250 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 2.3643. Min Range: -2.3643

Max Act: 1.9456. Min Act: -0.0000

Data Index: 482935 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 2.3643. Min Range: -2.3643

Max Act: 1.9616. Min Act: -0.0000

Data Index: 523572 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 2.3643. Min Range: -2.3643

Max Act: 1.8574. Min Act: -0.0000

Data Index: 860200 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 2.3643. Min Range: -2.3643

Max Act: 1.9269. Min Act: -0.0000

Data Index: 1069423 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 2.3643. Min Range: -2.3643

Max Act: 1.8142. Min Act: -0.0000

Data Index: 309251 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 2.3643. Min Range: -2.3643

Max Act: 1.8825. Min Act: -0.0000

Data Index: 1297370 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 2.3643. Min Range: -2.3643

Max Act: 1.6200. Min Act: -0.0000

Data Index: 857815 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 2.3643. Min Range: -2.3643

Max Act: 1.9062. Min Act: -0.0000

Data Index: 115938 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 2.3643. Min Range: -2.3643

Max Act: 1.7926. Min Act: -0.0000

Data Index: 582426 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 2.3643. Min Range: -2.3643

Max Act: 1.7683. Min Act: -0.0000

Data Index: 1036915 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 2.3643. Min Range: -2.3643

Max Act: 1.6286. Min Act: -0.0000

Data Index: 766944 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 2.3643. Min Range: -2.3643

Max Act: 1.6292. Min Act: -0.0000

Data Index: 1244693 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 2.3643. Min Range: -2.3643

Max Act: 1.7249. Min Act: -0.0000

Data Index: 966965 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 2.3643. Min Range: -2.3643

Max Act: 1.6154. Min Act: -0.0000

Data Index: 1314581 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 2.3643. Min Range: -2.3643

Max Act: 1.6913. Min Act: -0.0000

Data Index: 971053 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 2.3643. Min Range: -2.3643

Max Act: 1.7993. Min Act: -0.0000

Data Index: 777606 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 2.3643. Min Range: -2.3643

Max Act: 1.6819. Min Act: -0.0000

Data Index: 374393 (C4 (Web Text))

Max Activating Token Index: 960