Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2359 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.6952. Min Act: -0.0000

Data Index: 729960 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.6260. Min Act: -0.0000

Data Index: 378086 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.6093. Min Act: -0.0001

Data Index: 301191 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5647. Min Act: -0.0001

Data Index: 709846 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5478. Min Act: -0.0001

Data Index: 340141 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5414. Min Act: -0.0000

Data Index: 359136 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5222. Min Act: -0.0000

Data Index: 158789 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5191. Min Act: -0.0000

Data Index: 379881 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5373. Min Act: -0.0001

Data Index: 953692 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5028. Min Act: -0.0000

Data Index: 342132 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.4146. Min Act: -0.0000

Data Index: 1137855 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.4742. Min Act: -0.0000

Data Index: 58924 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.4243. Min Act: -0.0001

Data Index: 446943 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.4843. Min Act: -0.0000

Data Index: 204347 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.4865. Min Act: -0.0001

Data Index: 74367 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.4615. Min Act: -0.0000

Data Index: 871121 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.4153. Min Act: -0.0000

Data Index: 819332 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.4784. Min Act: -0.0001

Data Index: 776563 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.4219. Min Act: -0.0001

Data Index: 1278964 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.4264. Min Act: -0.0001

Data Index: 658450 (C4 (Web Text))

Max Activating Token Index: 457