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

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

Neuron 2081 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: 0.4663. Min Range: -0.4663

Max Act: 0.4529. Min Act: -0.0001

Data Index: 19756 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4663. Min Act: -0.0001

Data Index: 735042 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4296. Min Act: -0.0001

Data Index: 460854 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4082. Min Act: -0.0001

Data Index: 327653 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4171. Min Act: -0.0001

Data Index: 416252 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4045. Min Act: -0.0001

Data Index: 745627 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4043. Min Act: -0.0001

Data Index: 1549278 (Python Code)

Max Activating Token Index: 737

Text #7

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4165. Min Act: -0.0001

Data Index: 1073817 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4129. Min Act: -0.0001

Data Index: 1135330 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4110. Min Act: -0.0001

Data Index: 148632 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4109. Min Act: -0.0001

Data Index: 798393 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4104. Min Act: -0.0001

Data Index: 1410208 (Python Code)

Max Activating Token Index: 455

Text #12

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4098. Min Act: -0.0001

Data Index: 1280961 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4094. Min Act: -0.0001

Data Index: 252812 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4084. Min Act: -0.0001

Data Index: 208 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3942. Min Act: -0.0001

Data Index: 481160 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3885. Min Act: -0.0001

Data Index: 357698 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4030. Min Act: -0.0001

Data Index: 712998 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4150. Min Act: -0.0001

Data Index: 978440 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3922. Min Act: -0.0001

Data Index: 43860 (C4 (Web Text))

Max Activating Token Index: 106