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

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

Neuron 2679 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.4265. Min Act: -0.0001

Data Index: 1263512 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.4125. Min Act: -0.0001

Data Index: 22332 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3978. Min Act: -0.0001

Data Index: 1270854 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3850. Min Act: -0.0001

Data Index: 628518 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3881. Min Act: -0.0001

Data Index: 153062 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3849. Min Act: -0.0001

Data Index: 21655 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3862. Min Act: -0.0001

Data Index: 897310 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3943. Min Act: -0.0001

Data Index: 132752 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3981. Min Act: -0.0001

Data Index: 1272920 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3786. Min Act: -0.0001

Data Index: 197093 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3785. Min Act: -0.0001

Data Index: 98930 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3778. Min Act: -0.0001

Data Index: 1150157 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3765. Min Act: -0.0001

Data Index: 335988 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3732. Min Act: -0.0001

Data Index: 1149786 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3719. Min Act: -0.0001

Data Index: 959363 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3616. Min Act: -0.0001

Data Index: 478817 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3830. Min Act: -0.0001

Data Index: 618111 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3517. Min Act: -0.0001

Data Index: 407070 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3603. Min Act: -0.0001

Data Index: 1014436 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3741. Min Act: -0.0001

Data Index: 489272 (C4 (Web Text))

Max Activating Token Index: 817