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

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

Neuron 1171 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.7870. Min Act: -0.0000

Data Index: 230209 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.8043. Min Act: -0.0000

Data Index: 1124196 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.7236. Min Act: -0.0000

Data Index: 1046297 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.6970. Min Act: -0.0000

Data Index: 610050 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.6490. Min Act: -0.0000

Data Index: 121247 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.6216. Min Act: -0.0000

Data Index: 384445 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.6338. Min Act: -0.0000

Data Index: 375547 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.6503. Min Act: -0.0000

Data Index: 578540 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.6274. Min Act: -0.0000

Data Index: 612153 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.6115. Min Act: -0.0000

Data Index: 555047 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.6285. Min Act: -0.0000

Data Index: 400843 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.6148. Min Act: -0.0000

Data Index: 378218 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.6481. Min Act: -0.0000

Data Index: 1015441 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.6051. Min Act: -0.0000

Data Index: 300485 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.5989. Min Act: -0.0000

Data Index: 190392 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.6126. Min Act: -0.0000

Data Index: 165452 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.5859. Min Act: -0.0000

Data Index: 112768 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.5975. Min Act: -0.0000

Data Index: 396574 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.5775. Min Act: -0.0000

Data Index: 908844 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.5973. Min Act: -0.0001

Data Index: 1248471 (C4 (Web Text))

Max Activating Token Index: 703