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

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

Neuron 2446 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3829. Min Range: -2.3829

Max Act: 2.3829. Min Act: -0.0000

Data Index: 1453205 (Python Code)

Max Activating Token Index: 465

Text #1

Max Range: 2.3829. Min Range: -2.3829

Max Act: 1.9965. Min Act: -0.0000

Data Index: 1495190 (Python Code)

Max Activating Token Index: 955

Text #2

Max Range: 2.3829. Min Range: -2.3829

Max Act: 1.8721. Min Act: -0.0000

Data Index: 1474274 (Python Code)

Max Activating Token Index: 275

Text #3

Max Range: 2.3829. Min Range: -2.3829

Max Act: 1.7094. Min Act: -0.0000

Data Index: 686206 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 2.3829. Min Range: -2.3829

Max Act: 1.7460. Min Act: -0.0000

Data Index: 568831 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 2.3829. Min Range: -2.3829

Max Act: 1.6166. Min Act: -0.0000

Data Index: 927677 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 2.3829. Min Range: -2.3829

Max Act: 1.4274. Min Act: -0.0000

Data Index: 421141 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 2.3829. Min Range: -2.3829

Max Act: 1.6025. Min Act: -0.0000

Data Index: 1504241 (Python Code)

Max Activating Token Index: 670

Text #8

Max Range: 2.3829. Min Range: -2.3829

Max Act: 1.5779. Min Act: -0.0000

Data Index: 939436 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 2.3829. Min Range: -2.3829

Max Act: 1.5725. Min Act: -0.0000

Data Index: 1650551 (Python Code)

Max Activating Token Index: 85

Text #10

Max Range: 2.3829. Min Range: -2.3829

Max Act: 1.5711. Min Act: -0.0000

Data Index: 1397494 (Python Code)

Max Activating Token Index: 382

Text #11

Max Range: 2.3829. Min Range: -2.3829

Max Act: 1.6097. Min Act: -0.0000

Data Index: 1633639 (Python Code)

Max Activating Token Index: 773

Text #12

Max Range: 2.3829. Min Range: -2.3829

Max Act: 1.5156. Min Act: -0.0000

Data Index: 1485343 (Python Code)

Max Activating Token Index: 879

Text #13

Max Range: 2.3829. Min Range: -2.3829

Max Act: 1.5291. Min Act: -0.0000

Data Index: 1475855 (Python Code)

Max Activating Token Index: 603

Text #14

Max Range: 2.3829. Min Range: -2.3829

Max Act: 1.3795. Min Act: -0.0000

Data Index: 1408380 (Python Code)

Max Activating Token Index: 855

Text #15

Max Range: 2.3829. Min Range: -2.3829

Max Act: 1.5845. Min Act: -0.0000

Data Index: 501401 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 2.3829. Min Range: -2.3829

Max Act: 1.4982. Min Act: -0.0000

Data Index: 1409190 (Python Code)

Max Activating Token Index: 200

Text #17

Max Range: 2.3829. Min Range: -2.3829

Max Act: 1.5102. Min Act: -0.0000

Data Index: 1649415 (Python Code)

Max Activating Token Index: 296

Text #18

Max Range: 2.3829. Min Range: -2.3829

Max Act: 1.4347. Min Act: -0.0000

Data Index: 1419178 (Python Code)

Max Activating Token Index: 211

Text #19

Max Range: 2.3829. Min Range: -2.3829

Max Act: 1.4371. Min Act: -0.0000

Data Index: 1438033 (Python Code)

Max Activating Token Index: 160