Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3007 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2315. Min Range: -2.2315

Max Act: 2.2315. Min Act: -0.0000

Data Index: 534253 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 2.2315. Min Range: -2.2315

Max Act: 2.0646. Min Act: -0.0000

Data Index: 458208 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 2.2315. Min Range: -2.2315

Max Act: 2.1787. Min Act: -0.0000

Data Index: 290461 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 2.2315. Min Range: -2.2315

Max Act: 2.0596. Min Act: -0.0000

Data Index: 1257937 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 2.2315. Min Range: -2.2315

Max Act: 1.8441. Min Act: -0.0000

Data Index: 1013391 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 2.2315. Min Range: -2.2315

Max Act: 1.8893. Min Act: -0.0000

Data Index: 997851 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 2.2315. Min Range: -2.2315

Max Act: 2.0071. Min Act: -0.0000

Data Index: 477056 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 2.2315. Min Range: -2.2315

Max Act: 1.9945. Min Act: -0.0000

Data Index: 741239 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 2.2315. Min Range: -2.2315

Max Act: 1.9380. Min Act: -0.0000

Data Index: 836687 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 2.2315. Min Range: -2.2315

Max Act: 1.8063. Min Act: -0.0000

Data Index: 419697 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 2.2315. Min Range: -2.2315

Max Act: 1.9071. Min Act: -0.0000

Data Index: 138050 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 2.2315. Min Range: -2.2315

Max Act: 2.0123. Min Act: -0.0000

Data Index: 326956 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 2.2315. Min Range: -2.2315

Max Act: 2.0969. Min Act: -0.0000

Data Index: 886765 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 2.2315. Min Range: -2.2315

Max Act: 1.8503. Min Act: -0.0000

Data Index: 212762 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 2.2315. Min Range: -2.2315

Max Act: 1.8460. Min Act: -0.0000

Data Index: 522803 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 2.2315. Min Range: -2.2315

Max Act: 1.8286. Min Act: -0.0000

Data Index: 772497 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 2.2315. Min Range: -2.2315

Max Act: 1.8329. Min Act: -0.0000

Data Index: 1065130 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 2.2315. Min Range: -2.2315

Max Act: 1.9365. Min Act: -0.0000

Data Index: 247714 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 2.2315. Min Range: -2.2315

Max Act: 1.8401. Min Act: -0.0000

Data Index: 796535 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 2.2315. Min Range: -2.2315

Max Act: 1.8217. Min Act: -0.0000

Data Index: 940962 (C4 (Web Text))

Max Activating Token Index: 113