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

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

Neuron 2661 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.8339. Min Act: -0.0001

Data Index: 1465148 (Python Code)

Max Activating Token Index: 587

Text #1

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.7407. Min Act: -0.0001

Data Index: 1657034 (Python Code)

Max Activating Token Index: 680

Text #2

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.7612. Min Act: -0.0001

Data Index: 1419398 (Python Code)

Max Activating Token Index: 269

Text #3

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.7590. Min Act: -0.0001

Data Index: 1655451 (Python Code)

Max Activating Token Index: 146

Text #4

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.7617. Min Act: -0.0001

Data Index: 191970 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.7297. Min Act: -0.0001

Data Index: 871157 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.7455. Min Act: -0.0001

Data Index: 1523605 (Python Code)

Max Activating Token Index: 309

Text #7

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.7155. Min Act: -0.0001

Data Index: 818516 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6959. Min Act: -0.0001

Data Index: 1325183 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6851. Min Act: -0.0001

Data Index: 1560407 (Python Code)

Max Activating Token Index: 242

Text #10

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6608. Min Act: -0.0001

Data Index: 1350753 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6818. Min Act: -0.0001

Data Index: 732443 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6771. Min Act: -0.0001

Data Index: 1140459 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6687. Min Act: -0.0001

Data Index: 582951 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6704. Min Act: -0.0001

Data Index: 1347490 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.7169. Min Act: -0.0001

Data Index: 871649 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6759. Min Act: -0.0001

Data Index: 257121 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6515. Min Act: -0.0001

Data Index: 776804 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6588. Min Act: -0.0001

Data Index: 488448 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6511. Min Act: -0.0001

Data Index: 616563 (C4 (Web Text))

Max Activating Token Index: 25