Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2539 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5253. Min Range: -1.5253

Max Act: 1.5253. Min Act: -0.0001

Data Index: 884139 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 1.5253. Min Range: -1.5253

Max Act: 1.5070. Min Act: -0.0001

Data Index: 9739 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 1.5253. Min Range: -1.5253

Max Act: 1.2875. Min Act: -0.0001

Data Index: 457664 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 1.5253. Min Range: -1.5253

Max Act: 1.1630. Min Act: -0.0001

Data Index: 1208991 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 1.5253. Min Range: -1.5253

Max Act: 1.1525. Min Act: -0.0001

Data Index: 505616 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 1.5253. Min Range: -1.5253

Max Act: 1.3406. Min Act: -0.0001

Data Index: 825904 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 1.5253. Min Range: -1.5253

Max Act: 1.1730. Min Act: -0.0001

Data Index: 518587 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 1.5253. Min Range: -1.5253

Max Act: 1.2255. Min Act: -0.0001

Data Index: 1320742 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 1.5253. Min Range: -1.5253

Max Act: 1.2300. Min Act: -0.0001

Data Index: 62695 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 1.5253. Min Range: -1.5253

Max Act: 1.1228. Min Act: -0.0001

Data Index: 670606 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 1.5253. Min Range: -1.5253

Max Act: 1.2088. Min Act: -0.0001

Data Index: 1189690 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 1.5253. Min Range: -1.5253

Max Act: 1.2353. Min Act: -0.0001

Data Index: 726954 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 1.5253. Min Range: -1.5253

Max Act: 1.1752. Min Act: -0.0001

Data Index: 558640 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 1.5253. Min Range: -1.5253

Max Act: 1.2262. Min Act: -0.0001

Data Index: 633608 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 1.5253. Min Range: -1.5253

Max Act: 1.1525. Min Act: -0.0001

Data Index: 317027 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 1.5253. Min Range: -1.5253

Max Act: 1.1728. Min Act: -0.0001

Data Index: 1035829 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 1.5253. Min Range: -1.5253

Max Act: 1.1028. Min Act: -0.0001

Data Index: 1285368 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 1.5253. Min Range: -1.5253

Max Act: 1.0140. Min Act: -0.0001

Data Index: 44037 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 1.5253. Min Range: -1.5253

Max Act: 0.9821. Min Act: -0.0001

Data Index: 1312439 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 1.5253. Min Range: -1.5253

Max Act: 1.1862. Min Act: -0.0001

Data Index: 799358 (C4 (Web Text))

Max Activating Token Index: 151