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

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

Neuron 1732 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.6102. Min Act: -0.0001

Data Index: 356958 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.1786. Min Act: -0.0001

Data Index: 1191695 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 3.6102. Min Range: -3.6102

Max Act: 2.9680. Min Act: -0.0001

Data Index: 1089357 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.0726. Min Act: -0.0001

Data Index: 1322977 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.1068. Min Act: -0.0001

Data Index: 583494 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.1398. Min Act: -0.0001

Data Index: 183319 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 3.6102. Min Range: -3.6102

Max Act: 2.8786. Min Act: -0.0001

Data Index: 745628 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 3.6102. Min Range: -3.6102

Max Act: 2.6013. Min Act: -0.0001

Data Index: 70578 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 3.6102. Min Range: -3.6102

Max Act: 2.8665. Min Act: -0.0001

Data Index: 1001453 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 3.6102. Min Range: -3.6102

Max Act: 2.7287. Min Act: -0.0001

Data Index: 175992 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 3.6102. Min Range: -3.6102

Max Act: 2.5172. Min Act: -0.0001

Data Index: 849226 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 3.6102. Min Range: -3.6102

Max Act: 2.5061. Min Act: -0.0001

Data Index: 1197457 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 3.6102. Min Range: -3.6102

Max Act: 2.5164. Min Act: -0.0001

Data Index: 1288932 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 3.6102. Min Range: -3.6102

Max Act: 2.6298. Min Act: -0.0001

Data Index: 462616 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 3.6102. Min Range: -3.6102

Max Act: 2.6292. Min Act: -0.0001

Data Index: 67067 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 3.6102. Min Range: -3.6102

Max Act: 2.4995. Min Act: -0.0001

Data Index: 658920 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 3.6102. Min Range: -3.6102

Max Act: 2.6120. Min Act: -0.0001

Data Index: 1258132 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 3.6102. Min Range: -3.6102

Max Act: 2.4865. Min Act: -0.0001

Data Index: 348290 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 3.6102. Min Range: -3.6102

Max Act: 2.5829. Min Act: -0.0001

Data Index: 514052 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 3.6102. Min Range: -3.6102

Max Act: 2.4427. Min Act: -0.0001

Data Index: 895772 (C4 (Web Text))

Max Activating Token Index: 685